{
  "benchmark_line": "gamebench2",
  "comparability_tuples": [
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "balanced",
      "results_cut_id": "20260824_085407",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_kind": "full_freedom"
    },
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "baseline",
      "results_cut_id": "20260824_085407",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_kind": "full_freedom"
    },
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "intensive",
      "results_cut_id": "20260824_085407",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_kind": "full_freedom"
    },
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "mixed",
      "results_cut_id": "20260824_085407",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_kind": "full_freedom"
    },
    {
      "evaluation_family": "codegen_public_benchmark",
      "rating_method": "sequential_elo",
      "reasoning_effort": "aggregate",
      "results_cut_id": "20260824_085407",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_kind": "overall"
    }
  ],
  "generated_at": "2026-08-24T08:54:07Z",
  "public_release_id": "gb2-20260824-f35e2e58fce6",
  "results_cut_id": "gb2-20260824-f35e2e58fce6",
  "rows": [
    {
      "admitted_plugins": 8,
      "attempted_matches": 686,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 3,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 1.17244375,
        "mean": 0.7965692187500001,
        "median": 0.7419175,
        "min": 0.6308437499999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 6.372553750000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 87.33240524426331,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 31,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:27:52Z",
      "losses": 70,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 63.917443301992066,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 686,
      "rating_method": "sequential_elo",
      "raw_elo": 1847.0273809657585,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 87.33240524426331,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 585
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 604,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 1.91725,
        "mean": 1.58262125,
        "median": 1.5854,
        "min": 1.05322,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 12.660969999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 83.32037116335817,
      "contributing_entrants": null,
      "distinct_rated_opponents": 65,
      "draws": 72,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "infra_failures_excluded": 4,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:44:21Z",
      "losses": 91,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 67.5967962093199,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 604,
      "rating_method": "sequential_elo",
      "raw_elo": 1839.8742026911013,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 83.32037116335817,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 441
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 778,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 3,
        "max": 2.09943,
        "mean": 1.379653125,
        "median": 1.3205149999999999,
        "min": 0.8875599999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 22.07445
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 80.00582303982328,
      "contributing_entrants": null,
      "distinct_rated_opponents": 55,
      "draws": 52,
      "eligibility_flag": true,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.8125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:44:12Z",
      "losses": 140,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 58.28936991672205,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 3,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.8125,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 778,
      "rating_method": "sequential_elo",
      "raw_elo": 1807.1235611426819,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 75.95868536285322,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 586
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1132,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 18,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.551725,
        "mean": 0.44617968750000003,
        "median": 0.45788,
        "min": 0.33828,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 7.1388750000000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 75.96881544186866,
      "contributing_entrants": null,
      "distinct_rated_opponents": 80,
      "draws": 160,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:35:16Z",
      "losses": 187,
      "max_score": 90.23843179247481,
      "measured_at": null,
      "min_score": 51.33723880160861,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1132,
      "rating_method": "sequential_elo",
      "raw_elo": 1778.4915205310851,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 73.47462325689973,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 785
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 642,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 15,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 2.2530275,
        "mean": 1.51903,
        "median": 1.4938600000000002,
        "min": 1.088255,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 12.152239999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 75.18390389272452,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 84,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T08:04:25Z",
      "losses": 74,
      "max_score": 95.06137796160141,
      "measured_at": null,
      "min_score": 38.881693886910185,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 639,
      "rating_method": "sequential_elo",
      "raw_elo": 1792.293994442148,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 72.71548175880062,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 481
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1286,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 107,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.5221625,
        "mean": 0.2856328125,
        "median": 0.2536225,
        "min": 0.2178175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 4.570124999999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 70.79162335985623,
      "contributing_entrants": null,
      "distinct_rated_opponents": 102,
      "draws": 261,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-21T15:53:02Z",
      "losses": 215,
      "max_score": 90.96243393579934,
      "measured_at": null,
      "min_score": 51.301004509305145,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1285,
      "rating_method": "sequential_elo",
      "raw_elo": 1745.7190424540813,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 68.46740765742071,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 809
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 545,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 4.4173,
        "mean": 2.7356843750000004,
        "median": 2.536595,
        "min": 2.045485,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.885475000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 69.79119288611703,
      "contributing_entrants": null,
      "distinct_rated_opponents": 65,
      "draws": 107,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:35:52Z",
      "losses": 115,
      "max_score": 93.82012264656494,
      "measured_at": null,
      "min_score": 31.278757459984458,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 544,
      "rating_method": "sequential_elo",
      "raw_elo": 1748.5057765730885,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 67.49982310677103,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 322
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 572,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 1.38945,
        "mean": 0.93123625,
        "median": 0.95991,
        "min": 0.36561,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 7.44989
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.9074703488038,
      "contributing_entrants": null,
      "distinct_rated_opponents": 65,
      "draws": 71,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:23:19Z",
      "losses": 146,
      "max_score": 79.45887582150341,
      "measured_at": null,
      "min_score": 53.60093706896381,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 572,
      "rating_method": "sequential_elo",
      "raw_elo": 1706.0432881530799,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 66.64511476210285,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 355
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 690,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 37,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.24740375,
        "mean": 0.229063125,
        "median": 0.23243875,
        "min": 0.20046375,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.8325049999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 66.4740090857523,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 98,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T05:21:14Z",
      "losses": 149,
      "max_score": 90.14837149543118,
      "measured_at": null,
      "min_score": 36.8828822319936,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 690,
      "rating_method": "sequential_elo",
      "raw_elo": 1673.4699526261177,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 66.4740090857523,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 443
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 528,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.6981,
        "mean": 0.5046499999999999,
        "median": 0.511355,
        "min": 0.33027,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.0372
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.30128747589305,
      "contributing_entrants": null,
      "distinct_rated_opponents": 57,
      "draws": 57,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:34:24Z",
      "losses": 117,
      "max_score": 77.40648648738761,
      "measured_at": null,
      "min_score": 56.05592222052655,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 524,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.177675643524,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 66.05883395789598,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 350
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1728,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 190,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.531673125,
        "mean": 0.47737264687500003,
        "median": 0.48302475,
        "min": 0.3855675,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 7.6379623500000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 67.94613426450412,
      "contributing_entrants": null,
      "distinct_rated_opponents": 65,
      "draws": 285,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:51:05Z",
      "losses": 436,
      "max_score": 91.56194509481253,
      "measured_at": null,
      "min_score": 48.9850812289486,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1724,
      "rating_method": "sequential_elo",
      "raw_elo": 1695.9244161237407,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 63.2310027037512,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1003
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1220,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 42,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "evidence_basis": "Provider-reported",
        "max": 0.13495079999999998,
        "mean": 0.07455065,
        "median": 0.0607138,
        "min": 0.0448404,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.5964052
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 62.11035404695588,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 233,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:27:52Z",
      "losses": 327,
      "max_score": 91.324739517719,
      "measured_at": null,
      "min_score": 32.41381726074275,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1220,
      "rating_method": "sequential_elo",
      "raw_elo": 1658.1990934445623,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 62.11035404695588,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 660
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 602,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 44,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 12.137519999999999,
        "mean": 8.1660015625,
        "median": 8.18098,
        "min": 4.7142525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 65.32801249999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 57.52510803929284,
      "contributing_entrants": null,
      "distinct_rated_opponents": 69,
      "draws": 137,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:35:30Z",
      "losses": 185,
      "max_score": 76.39149789263541,
      "measured_at": null,
      "min_score": 41.41290592375142,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 602,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.7319965637298,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 57.52510803929284,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 280
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 746,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 9,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "max": 0.0878628,
        "mean": 0.0635932,
        "median": 0.06199639999999999,
        "min": 0.0498884,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.5087456
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 57.180934977713015,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 170,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:42:30Z",
      "losses": 208,
      "max_score": 87.21199208118166,
      "measured_at": null,
      "min_score": 28.15047326894219,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 744,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.1880129737478,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 57.180934977713015,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 366
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1813,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 120,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 44
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.3888165,
        "mean": 0.26060548125,
        "median": 0.24728879999999998,
        "min": 0.17802225,
        "recorded_attempt_count": 44,
        "run_count": 16,
        "total": 4.169687699999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 57.72594535990394,
      "contributing_entrants": null,
      "distinct_rated_opponents": 107,
      "draws": 443,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-08"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:38:44Z",
      "losses": 428,
      "max_score": 90.59930630959718,
      "measured_at": null,
      "min_score": 16.174375669656794,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1813,
      "rating_method": "sequential_elo",
      "raw_elo": 1648.3308135308127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 55.83069925202183,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 942
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 698,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 17,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.15394249999999998,
        "mean": 0.12786562499999998,
        "median": 0.13029000000000002,
        "min": 0.10071375,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.022925
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 55.76248795572135,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 161,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T03:03:24Z",
      "losses": 172,
      "max_score": 78.74292256811869,
      "measured_at": null,
      "min_score": 27.127464596852075,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 698,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.2432870557532,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 55.76248795572135,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 365
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 638,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 60,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "max": 0.5145615,
        "mean": 0.34875300000000004,
        "median": 0.335163,
        "min": 0.254883,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 2.790024
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 55.362830501043646,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 195,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:04:12Z",
      "losses": 156,
      "max_score": 84.5317048418163,
      "measured_at": null,
      "min_score": 26.743400089025748,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.7519290982525,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 55.362830501043646,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 285
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 730,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 59,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.4120425,
        "mean": 0.283374375,
        "median": 0.26543625,
        "min": 0.2124125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 2.2669949999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 54.95759913349221,
      "contributing_entrants": null,
      "distinct_rated_opponents": 46,
      "draws": 211,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:23:52Z",
      "losses": 170,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 25.90894221037543,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 730,
      "rating_method": "sequential_elo",
      "raw_elo": 1626.7886478001335,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 54.95759913349221,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 349
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 684,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.50466,
        "mean": 0.35099375,
        "median": 0.321349,
        "min": 0.220732,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 2.8079499999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 54.29911281921975,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 160,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:13:25Z",
      "losses": 198,
      "max_score": 83.58905380078096,
      "measured_at": null,
      "min_score": 18.648854275319852,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 684,
      "rating_method": "sequential_elo",
      "raw_elo": 1588.332224513131,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 54.29911281921975,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 326
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1338,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 133,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "max": 0.1077678,
        "mean": 0.076003275,
        "median": 0.070269,
        "min": 0.0550338,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.6080262
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.41264234414682,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 396,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T04:48:24Z",
      "losses": 361,
      "max_score": 98.88106339111127,
      "measured_at": null,
      "min_score": 22.928875872336782,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 1.0,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1338,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.9446710142445,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 53.41264234414682,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 581
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 676,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 103,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.58673,
        "mean": 0.44285687500000004,
        "median": 0.4176025,
        "min": 0.34269,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.542855
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.08734861096748,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 224,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:43:10Z",
      "losses": 187,
      "max_score": 73.85605709393225,
      "measured_at": null,
      "min_score": 37.548190679008606,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 676,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.9362133985667,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 53.08734861096748,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 265
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 597,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 24,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.060198249999999995,
        "mean": 0.047021,
        "median": 0.04824225,
        "min": 0.0324825,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.37616799999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 54.56046464326638,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 135,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T02:44:09Z",
      "losses": 156,
      "max_score": 79.71591004614217,
      "measured_at": null,
      "min_score": 28.93634004616261,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": 0.875,
      "provider": "Other",
      "provider_key": "other",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 597,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.5345465563757,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 52.76914693309831,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 306
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 682,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 53,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0377622,
        "mean": 0.030833324999999998,
        "median": 0.031411375,
        "min": 0.0247604,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.24666659999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.76207198216008,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 200,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:55:05Z",
      "losses": 175,
      "max_score": 83.09168848413222,
      "measured_at": null,
      "min_score": 24.22675683362329,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 681,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.9767875156492,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 52.76207198216008,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 306
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 678,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 83,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.144235,
        "mean": 0.12174125,
        "median": 0.121475,
        "min": 0.09594,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.9739300000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 48.974391609272004,
      "contributing_entrants": null,
      "distinct_rated_opponents": 75,
      "draws": 237,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:02:30Z",
      "losses": 187,
      "max_score": 70.0969711174775,
      "measured_at": null,
      "min_score": 26.56425672722357,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 678,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.2756966245358,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 48.974391609272004,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 254
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1188,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 147,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "max": 0.4398702,
        "mean": 0.29041619999999996,
        "median": 0.301782,
        "min": 0.095232,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 16
        },
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 2.3233296
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.63127725653765,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 376,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T07:54:09Z",
      "losses": 385,
      "max_score": 68.46351429427254,
      "measured_at": null,
      "min_score": 20.275423642118344,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 1.0,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1177,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.909059018083,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 47.63127725653765,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 416
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 554,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 20,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.190125,
        "mean": 0.15785312499999998,
        "median": 0.15388000000000002,
        "min": 0.131495,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.2628249999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 49.15100352600054,
      "contributing_entrants": null,
      "distinct_rated_opponents": 74,
      "draws": 147,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:47:33Z",
      "losses": 161,
      "max_score": 73.81276758326433,
      "measured_at": null,
      "min_score": 19.14734246410184,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 554,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.4818809927503,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 47.53728810652374,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 246
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 670,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 97,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.34174499999999997,
        "mean": 0.217940625,
        "median": 0.19638,
        "min": 0.14813,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.743525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.42768341066297,
      "contributing_entrants": null,
      "distinct_rated_opponents": 76,
      "draws": 266,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:49:27Z",
      "losses": 166,
      "max_score": 80.14817108632784,
      "measured_at": null,
      "min_score": 15.975113871358344,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 670,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.8421897562826,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 47.42768341066297,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 238
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 466,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 58,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.6921525,
        "mean": 0.48907706250000005,
        "median": 0.483741,
        "min": 0.401826,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 3.9126165
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.77386093048303,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 133,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:04:52Z",
      "losses": 168,
      "max_score": 80.84833683146083,
      "measured_at": null,
      "min_score": 24.174721344647317,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 466,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.3773057677738,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 47.25040169728176,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 725,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 49,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.325659,
        "mean": 0.25189603125,
        "median": 0.25775625,
        "min": 0.169101,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 2.0151682500000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.81264427076511,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 219,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:55:18Z",
      "losses": 217,
      "max_score": 58.26867546532442,
      "measured_at": null,
      "min_score": 21.89947442115403,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 723,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.8496538432216,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 46.81264427076511,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 287
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 566,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.072978,
        "mean": 0.048872,
        "median": 0.046325000000000005,
        "min": 0.037309999999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.390976
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.20675055685002,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 143,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:17:46Z",
      "losses": 185,
      "max_score": 62.569827155594346,
      "measured_at": null,
      "min_score": 36.401476747289344,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.2514541628454,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 46.72264602793167,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 238
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1225,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 126,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "max": 0.0992248,
        "mean": 0.07433795,
        "median": 0.0774068,
        "min": 0.0424244,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.5947036
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.42173740142161,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 383,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T13:45:16Z",
      "losses": 372,
      "max_score": 85.5368320379681,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1225,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.199220453627,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 46.42173740142161,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 470
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 514,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.10909930499999998,
        "mean": 0.082847753875,
        "median": 0.084146916,
        "min": 0.03951746,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.662782031
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 49.79095279932275,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 125,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:41Z",
      "losses": 201,
      "max_score": 77.21666620850746,
      "measured_at": null,
      "min_score": 32.98184099437737,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": 0.75,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 514,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.202012164198,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 46.33570261437304,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 641,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 68,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.45464499999999997,
        "mean": 0.28201406249999994,
        "median": 0.2695775,
        "min": 0.17401125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 2.2561125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.24774896841963,
      "contributing_entrants": null,
      "distinct_rated_opponents": 77,
      "draws": 193,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:05:23Z",
      "losses": 230,
      "max_score": 67.70578978678658,
      "measured_at": null,
      "min_score": 19.976294071045,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 640,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.120873679543,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 46.24774896841963,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 217
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 566,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 106,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.08827968,
        "mean": 0.05437612,
        "median": 0.0574344,
        "min": 0.00733824,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.43500896
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.749573048252884,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 176,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:48:47Z",
      "losses": 188,
      "max_score": 72.53293912084276,
      "measured_at": null,
      "min_score": 22.584554928424122,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": 0.75,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.7798004283432,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 43.50537983965268,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 720,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 64,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.179715,
        "mean": 0.09608781250000001,
        "median": 0.08063500000000001,
        "min": 0.0656625,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.7687025000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.47321666269807,
      "contributing_entrants": null,
      "distinct_rated_opponents": 42,
      "draws": 216,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T07:54:09Z",
      "losses": 240,
      "max_score": 75.15416974608023,
      "measured_at": null,
      "min_score": 17.905822221963863,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 720,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.9242609213122,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 43.47321666269807,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 264
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 700,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.24673750000000003,
        "mean": 0.16744,
        "median": 0.15809499999999999,
        "min": 0.108735,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 1.3395199999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.44652688282063,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 259,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:18:32Z",
      "losses": 212,
      "max_score": 60.64978060082346,
      "measured_at": null,
      "min_score": 21.8994809309449,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 700,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.9152130042207,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 43.44652688282063,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 229
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 494,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 73,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "max": 0.14831665,
        "mean": 0.06589574925,
        "median": 0.044104765,
        "min": 0.0155414,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.527165994
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.245062052265894,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 195,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T03:34:47Z",
      "losses": 138,
      "max_score": 66.27613202821979,
      "measured_at": null,
      "min_score": 19.216835075427902,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 494,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.3698922933597,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 43.245062052265894,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 2801,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 219,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 32,
          "local_standard_estimate": 8
        },
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 13,
        "max": 0.1097735,
        "mean": 0.091486,
        "median": 0.08840574999999999,
        "min": 0.0773785,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 40
        },
        "recorded_attempt_count": 32,
        "run_count": 32,
        "token_priced_attempt_count": 8,
        "total": 2.927552
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 48.78091738661657,
      "contributing_entrants": null,
      "distinct_rated_opponents": 62,
      "draws": 282,
      "eligibility_flag": true,
      "entry_count": 19,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.59375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T13:45:04Z",
      "losses": 1224,
      "max_score": 56.03900598894137,
      "measured_at": null,
      "min_score": 39.158820258821116,
      "model_code_failure_rate": 0.40625,
      "model_code_failures": 13,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.59375,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2801,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.7151807795326,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.82041472033598,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1295
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 560,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 67,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.21477374999999999,
        "mean": 0.17756265624999998,
        "median": 0.17285124999999998,
        "min": 0.1418975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.42050125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.25870820023652,
      "contributing_entrants": null,
      "distinct_rated_opponents": 68,
      "draws": 156,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:19:06Z",
      "losses": 204,
      "max_score": 62.86088508787239,
      "measured_at": null,
      "min_score": 21.501856921354634,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 560,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.5946476760857,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.80561559285842,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 998,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 85,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "evidence_basis": "Provider-reported",
        "max": 0.047757869999999994,
        "mean": 0.022448211274999998,
        "median": 0.017169796,
        "min": 0.0106770175,
        "recorded_attempt_count": 24,
        "run_count": 16,
        "total": 0.3591713804
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 42.77028062419599,
      "contributing_entrants": null,
      "distinct_rated_opponents": 75,
      "draws": 327,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T20:23:06Z",
      "losses": 346,
      "max_score": 59.57776973557898,
      "measured_at": null,
      "min_score": 18.537461190466654,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 998,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.3430410272745,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.77028062419599,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 325
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 652,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 99,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.12185499999999999,
        "mean": 0.09110296875000001,
        "median": 0.09280125,
        "min": 0.0343775,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.7288237500000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.10198903600353,
      "contributing_entrants": null,
      "distinct_rated_opponents": 69,
      "draws": 240,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:35:11Z",
      "losses": 203,
      "max_score": 79.13676897206143,
      "measured_at": null,
      "min_score": 15.302941621960535,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": 0.875,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 652,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.7786636926899,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.65404179929354,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 209
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 572,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 12,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.226689264,
        "mean": 0.16037539425,
        "median": 0.140728509,
        "min": 0.10689655,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 1.2830031539999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 45.58338513665577,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 163,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-06"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:26:41Z",
      "losses": 193,
      "max_score": 63.086489595554106,
      "measured_at": null,
      "min_score": 23.435946683398193,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": 0.75,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 572,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.8922747479967,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.42011970249428,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 216
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 574,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 94,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.03912625,
        "mean": 0.022799843750000003,
        "median": 0.021642500000000002,
        "min": 0.015285,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.18239875
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.48832517883199,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 190,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:33:39Z",
      "losses": 194,
      "max_score": 68.87219421844685,
      "measured_at": null,
      "min_score": 24.982247392476896,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": 0.875,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 568,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.5470816100574,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.06052562492911,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 184
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 662,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 101,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.1192425,
        "mean": 0.0683559375,
        "median": 0.06152125,
        "min": 0.0542775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 0.6063375
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 43.16044727061799,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 265,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.7777777777777778,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:05:30Z",
      "losses": 206,
      "max_score": 55.20092432661375,
      "measured_at": null,
      "min_score": 28.236124905450517,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 660,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.412487739949,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 41.90808402618568,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 189
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 652,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 79,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.09459400000000001,
        "mean": 0.0571955,
        "median": 0.043012,
        "min": 0.032534,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 0.45756399999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.47586576190677,
      "contributing_entrants": null,
      "distinct_rated_opponents": 83,
      "draws": 228,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:31Z",
      "losses": 224,
      "max_score": 63.331047607164344,
      "measured_at": null,
      "min_score": 18.508036486618778,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 651,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.0273047777948,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 41.47586576190677,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 199
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 675,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 55,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.07847,
        "mean": 0.06167125,
        "median": 0.061313,
        "min": 0.051588,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.49337
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.22590804755895,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 190,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:40:55Z",
      "losses": 272,
      "max_score": 57.13966476484938,
      "measured_at": null,
      "min_score": 18.901290276570073,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 675,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.8812004216356,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 41.22590804755895,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 213
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 675,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.08884,
        "mean": 0.06562375000000001,
        "median": 0.062855,
        "min": 0.049908,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.5249900000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.94075981647538,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 200,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T07:22:40Z",
      "losses": 266,
      "max_score": 52.37264260162897,
      "measured_at": null,
      "min_score": 28.897713502544164,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 675,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.0739205750247,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 40.94075981647538,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 209
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 594,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 117,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.029078938,
        "mean": 0.015562441375000001,
        "median": 0.013116718500000001,
        "min": 0.005612805,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.124499531
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.13826236852083,
      "contributing_entrants": null,
      "distinct_rated_opponents": 74,
      "draws": 207,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:18:01Z",
      "losses": 187,
      "max_score": 66.56206174162008,
      "measured_at": null,
      "min_score": 22.057846645260756,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 594,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.5101689138505,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 40.75478779311221,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 2243,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 310,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.0222516,
        "mean": 0.01697319375,
        "median": 0.015739925000000002,
        "min": 0.012759,
        "recorded_attempt_count": 34,
        "run_count": 16,
        "total": 0.27157109999999995
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 41.236974524375064,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 730,
      "eligibility_flag": true,
      "entry_count": 15,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:51:52Z",
      "losses": 845,
      "max_score": 73.02102977984342,
      "measured_at": null,
      "min_score": 10.571254109747576,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.9375,
      "provider": "Google",
      "provider_key": "google",
      "rank": 49,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2237,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.0623223001046,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 40.576969969102905,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 662
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 688,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 42,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "max": 0.03564825,
        "mean": 0.0239263125,
        "median": 0.02294625,
        "min": 0.01939525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.1914105
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.239933673861195,
      "contributing_entrants": null,
      "distinct_rated_opponents": 43,
      "draws": 163,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:38:06Z",
      "losses": 299,
      "max_score": 59.44710258784996,
      "measured_at": null,
      "min_score": 16.944819699504418,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": 50,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 688,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.5633851043926,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 40.239933673861195,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 226
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 689,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 69,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.011164349999999998,
        "mean": 0.00631805625,
        "median": 0.005847,
        "min": 0.00434295,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.05054445
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.169901679730685,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 217,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:38:55Z",
      "losses": 268,
      "max_score": 61.35124581231818,
      "measured_at": null,
      "min_score": 25.07186922308482,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 51,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 688,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.6454918535003,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 40.169901679730685,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 203
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1028,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 72,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.034210525000000006,
        "mean": 0.024715571875,
        "median": 0.0256067375,
        "min": 0.01676735,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 25
        },
        "run_count": 16,
        "token_priced_attempt_count": 25,
        "total": 0.39544915
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 42.61298325940131,
      "contributing_entrants": null,
      "distinct_rated_opponents": 79,
      "draws": 200,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:55:07Z",
      "losses": 416,
      "max_score": 63.14422335372282,
      "measured_at": null,
      "min_score": 15.136633992883711,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 52,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1026,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.270076244519,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 39.655849282035284,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 410
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 726,
      "canonical_public_row_identity": "publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 104,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "max": 0.07439860000000001,
        "mean": 0.060660574999999994,
        "median": 0.0565846,
        "min": 0.0485456,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.48528459999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.4814143462601,
      "contributing_entrants": null,
      "distinct_rated_opponents": 78,
      "draws": 276,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:34:43Z",
      "losses": 241,
      "max_score": 67.9767252117913,
      "measured_at": null,
      "min_score": 21.895370370120215,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 53,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 726,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.375862707454,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 39.4814143462601,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 209
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 612,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 167,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.156555,
        "mean": 0.1422525,
        "median": 0.14850249999999998,
        "min": 0.12078,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.13802
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.54520036195957,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 318,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:23:57Z",
      "losses": 157,
      "max_score": 53.951577978721,
      "measured_at": null,
      "min_score": 19.58339791797017,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 54,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 612,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.2701277698927,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 39.214028863594145,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 474,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 87,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0221782524,
        "mean": 0.00999808046,
        "median": 0.009941171,
        "min": 0.00212373,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.07998464368000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.58875401302814,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 135,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:43:54Z",
      "losses": 186,
      "max_score": 72.31048780319064,
      "measured_at": null,
      "min_score": 24.79810278001538,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.75,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 55,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 474,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.709764391484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 38.70269656852593,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1217,
      "canonical_public_row_identity": "publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 237,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.00407402,
        "mean": 0.0029986699999999997,
        "median": 0.00314426,
        "min": 0.0012446800000000002,
        "recorded_attempt_count": 33,
        "run_count": 14,
        "total": 0.04176386
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 39.52658657172093,
      "contributing_entrants": null,
      "distinct_rated_opponents": 113,
      "draws": 423,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T23:51:52Z",
      "losses": 408,
      "max_score": 57.87934682152756,
      "measured_at": null,
      "min_score": 19.31198981966688,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 2,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Other",
      "provider_key": "other",
      "rank": 56,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1209,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.4068445555506,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 5,
      "repaired_rate": 0.35714285714285715,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 38.03230207729145,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 378
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 2451,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 307,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "max": 0.07826175,
        "mean": 0.05584070625,
        "median": 0.0541695,
        "min": 0.0411735,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 0.8934513
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 37.771112166458195,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 861,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 12,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T13:45:16Z",
      "losses": 916,
      "max_score": 55.01429727686298,
      "measured_at": null,
      "min_score": 17.43890191914832,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 57,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2447,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.2795842311339,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 37.771112166458195,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 670
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 524,
      "canonical_public_row_identity": "publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 26,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.09803328,
        "mean": 0.0253809975,
        "median": 0.00943521,
        "min": 0.00639384,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.20304798
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.388823983582036,
      "contributing_entrants": null,
      "distinct_rated_opponents": 74,
      "draws": 119,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:33:21Z",
      "losses": 198,
      "max_score": 52.04366523994301,
      "measured_at": null,
      "min_score": 16.460871449147128,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": 0.75,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 58,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 524,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.0405300009095,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 37.58603585254086,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 207
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 478,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 97,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.001632522,
        "mean": 0.00126739675,
        "median": 0.001232095,
        "min": 0.00090937,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.010139174
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.95580492735129,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 212,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:08:37Z",
      "losses": 125,
      "max_score": 72.88756496655336,
      "measured_at": null,
      "min_score": 13.368124963630589,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": 0.75,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 59,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 472,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.0265940507213,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 37.18306621472872,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 810,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 101,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 25
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.00295601625,
        "mean": 0.0023887339375,
        "median": 0.002303478175,
        "min": 0.0017364400000000001,
        "recorded_attempt_count": 25,
        "run_count": 16,
        "total": 0.038219743
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 39.877338696159725,
      "contributing_entrants": null,
      "distinct_rated_opponents": 78,
      "draws": 254,
      "eligibility_flag": true,
      "entry_count": 11,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.4375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T20:23:03Z",
      "losses": 284,
      "max_score": 52.09231852753391,
      "measured_at": null,
      "min_score": 19.75239474357151,
      "model_code_failure_rate": 0.3125,
      "model_code_failures": 5,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.6875,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 60,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 810,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.2525601477869,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 36.3115127891146,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 272
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1020,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 137,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 27
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.01311555,
        "mean": 0.009215359375,
        "median": 0.009537575,
        "min": 0.004854125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 27
        },
        "run_count": 16,
        "token_priced_attempt_count": 27,
        "total": 0.14744575000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 38.748743740948335,
      "contributing_entrants": null,
      "distinct_rated_opponents": 82,
      "draws": 307,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-07"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:31Z",
      "losses": 386,
      "max_score": 56.113615016738166,
      "measured_at": null,
      "min_score": 19.627918979635304,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 61,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1014,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.9027140773467,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 36.05976920942859,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 321
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 621,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 109,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00444719,
        "mean": 0.0024656575,
        "median": 0.002155255,
        "min": 0.0011302579999999999,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.01972526
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.76717792204459,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 284,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-07"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:12:06Z",
      "losses": 203,
      "max_score": 46.6367117182378,
      "measured_at": null,
      "min_score": 21.69349452538362,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 62,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 621,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.7193844748713,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 35.560045662536105,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 518,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0097359,
        "mean": 0.0038356840999999994,
        "median": 0.0020557588,
        "min": 0.0014804776,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.0306854728
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.15729827406804,
      "contributing_entrants": null,
      "distinct_rated_opponents": 74,
      "draws": 116,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:45Z",
      "losses": 228,
      "max_score": 64.91216398908766,
      "measured_at": null,
      "min_score": 11.821654639826498,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.75,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 63,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 516,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.3193022973048,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 35.509367184055876,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 172
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1790,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 132,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0719635,
        "mean": 0.060768406250000004,
        "median": 0.0604727,
        "min": 0.05086675,
        "recorded_attempt_count": 50,
        "run_count": 16,
        "total": 0.9722945000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.646037321732905,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 435,
      "eligibility_flag": true,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.8125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:38:06Z",
      "losses": 812,
      "max_score": 54.3795837338173,
      "measured_at": null,
      "min_score": 26.141806979414127,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 64,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1789,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.5539477718055,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 35.44288232495812,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 542
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 554,
      "canonical_public_row_identity": "publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 41,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.007539277999999999,
        "mean": 0.0032457859375,
        "median": 0.0019568429999999998,
        "min": 0.001266762,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.031586439
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 37.22073036163209,
      "contributing_entrants": null,
      "distinct_rated_opponents": 76,
      "draws": 134,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.5555555555555556,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:51Z",
      "losses": 244,
      "max_score": 59.334280478082064,
      "measured_at": null,
      "min_score": 13.456150792860978,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 65,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 552,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.614172560139,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.95415224018846,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 174
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 61,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.01660212,
        "mean": 0.008820586750000001,
        "median": 0.007023681,
        "min": 0.00271606,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.07056469400000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.10085728904717,
      "contributing_entrants": null,
      "distinct_rated_opponents": 66,
      "draws": 151,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-05"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:31Z",
      "losses": 127,
      "max_score": 67.33768307109139,
      "measured_at": null,
      "min_score": 13.814065400064843,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 0.625,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 66,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.4188636801377,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.76612471599146,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 450,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 84,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.13485595000000003,
        "mean": 0.031792056250000006,
        "median": 0.0158481,
        "min": 0.0111232,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.38919240000000005
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 36.85807193397447,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 149,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-07"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.5555555555555556,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T03:28:04Z",
      "losses": 183,
      "max_score": 59.683472652436585,
      "measured_at": null,
      "min_score": 10.490412921476183,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 67,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 450,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.4077671585844,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.61357810936488,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1118,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 99,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0721503,
        "mean": 0.03677837187500001,
        "median": 0.0324098875,
        "min": 0.01945095,
        "recorded_attempt_count": 39,
        "run_count": 16,
        "total": 0.5884539500000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.58136186400597,
      "contributing_entrants": null,
      "distinct_rated_opponents": 92,
      "draws": 338,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.4375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:23:15Z",
      "losses": 465,
      "max_score": 68.95924601863939,
      "measured_at": null,
      "min_score": 12.558196600852206,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 68,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1118,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.3474412764353,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.04279310321619,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 315
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1312,
      "canonical_public_row_identity": "publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 271,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 38
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.021206376000000002,
        "mean": 0.01337795025,
        "median": 0.01381146,
        "min": 0.006392298,
        "recorded_attempt_count": 38,
        "run_count": 16,
        "total": 0.214047204
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 35.0433047714104,
      "contributing_entrants": null,
      "distinct_rated_opponents": 92,
      "draws": 471,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:24:42Z",
      "losses": 490,
      "max_score": 55.24795980739564,
      "measured_at": null,
      "min_score": 17.33176752068492,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": 0.875,
      "provider": "Other",
      "provider_key": "other",
      "rank": 69,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1308,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.959860969325,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 33.892770352939465,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 347
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.0
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.059131406213616,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 170,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:19:01Z",
      "losses": 228,
      "max_score": 50.38149773221454,
      "measured_at": null,
      "min_score": 27.8658776184786,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 70,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.9769156979073,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 33.55680290162351,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 168
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 676,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 46,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.038769960000000006,
        "mean": 0.023744302225,
        "median": 0.0230069837,
        "min": 0.0074361952000000005,
        "recorded_attempt_count": 20,
        "run_count": 9,
        "total": 0.21411433159999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 35.70195402420664,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 188,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:57:10Z",
      "losses": 278,
      "max_score": 47.485310968950955,
      "measured_at": null,
      "min_score": 24.206848131834946,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 71,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 676,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.3980166363503,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": 7,
      "repaired_rate": 0.7777777777777778,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 33.527862675169914,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 210
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 928,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 164,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.004911942999999999,
        "mean": 0.0031858331662499998,
        "median": 0.002947833025,
        "min": 0.001831717,
        "recorded_attempt_count": 24,
        "run_count": 16,
        "total": 0.05097333066
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 33.18602349106142,
      "contributing_entrants": null,
      "distinct_rated_opponents": 77,
      "draws": 328,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 10,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T20:22:51Z",
      "losses": 381,
      "max_score": 45.206404703543946,
      "measured_at": null,
      "min_score": 16.951008971108347,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 72,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 928,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.4522087437194,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 32.09646694130927,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 219
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 662,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 56,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 32
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0265755425,
        "mean": 0.018416099712499998,
        "median": 0.017703669999999998,
        "min": 0.0109615788,
        "recorded_attempt_count": 32,
        "run_count": 15,
        "total": 0.27207317540000003
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 35.24692202962718,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 298,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.08333333333333333,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-03",
        "GB2-06",
        "GB2-07"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T03:36:31Z",
      "losses": 231,
      "max_score": 55.90520340006413,
      "measured_at": null,
      "min_score": 20.078359431984563,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 4,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.6666666666666666,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 73,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 662,
      "rating_method": "sequential_elo",
      "raw_elo": 1436.2159615805783,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": 7,
      "repaired_rate": 0.5833333333333334,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.849189367051096,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 133
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 715,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 140,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.0456916,
        "mean": 0.031545040625,
        "median": 0.035551075,
        "min": 0.01864685,
        "recorded_attempt_count": 35,
        "run_count": 16,
        "total": 0.50472065
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.09170623264679,
      "contributing_entrants": null,
      "distinct_rated_opponents": 76,
      "draws": 303,
      "eligibility_flag": true,
      "entry_count": 9,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:29:54Z",
      "losses": 259,
      "max_score": 46.15142583047198,
      "measured_at": null,
      "min_score": 19.686387180079826,
      "model_code_failure_rate": 0.4375,
      "model_code_failures": 7,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.5625,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 74,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 715,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.5665099587284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.256334463397277,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1810,
      "canonical_public_row_identity": "publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 113,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 70
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.103943664,
        "mean": 0.0866474535,
        "median": 0.088847748,
        "min": 0.062759676,
        "recorded_attempt_count": 70,
        "run_count": 16,
        "total": 1.386359256
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 33.374227954450966,
      "contributing_entrants": null,
      "distinct_rated_opponents": 74,
      "draws": 425,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T10:07:05Z",
      "losses": 873,
      "max_score": 45.093217679579666,
      "measured_at": null,
      "min_score": 19.52045526776426,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 75,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1787,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.5200443945462,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.058218703193194,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 23,
      "wins": 489
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 322,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 106,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0597184625,
        "mean": 0.02467013555,
        "median": 0.0239011175,
        "min": 0.0040410944,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.1973610844
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.81793203271081,
      "contributing_entrants": null,
      "distinct_rated_opponents": 66,
      "draws": 203,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05",
        "GB2-07"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T20:22:54Z",
      "losses": 74,
      "max_score": 58.591838652401584,
      "measured_at": null,
      "min_score": 17.329198413600206,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.625,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 76,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.8056265285632,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 30.95800581695214,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 427,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 66,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0422995,
        "mean": 0.027492531250000004,
        "median": 0.025548,
        "min": 0.0204145,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.21994025
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.434364323170016,
      "contributing_entrants": null,
      "distinct_rated_opponents": 66,
      "draws": 120,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:05:18Z",
      "losses": 220,
      "max_score": 46.38961044453501,
      "measured_at": null,
      "min_score": 20.711146730771695,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.625,
      "provider": "Google",
      "provider_key": "google",
      "rank": 77,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 427,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.8471843700231,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 30.616960536836054,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 662,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 104,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.03021,
        "mean": 0.0183815625,
        "median": 0.015581250000000001,
        "min": 0.01245825,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.1470525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.595878931104806,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 298,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:24:08Z",
      "losses": 240,
      "max_score": 43.819799277453555,
      "measured_at": null,
      "min_score": 7.108412173273799,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 78,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 658,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.6062193453638,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 30.595878931104806,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 120
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 424,
      "canonical_public_row_identity": "publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 83,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 21
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.065385,
        "mean": 0.03551179375,
        "median": 0.032728425,
        "min": 0.0200767,
        "recorded_attempt_count": 21,
        "run_count": 9,
        "total": 0.3177278
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 34.48811830245897,
      "contributing_entrants": null,
      "distinct_rated_opponents": 68,
      "draws": 162,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-05"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:41:43Z",
      "losses": 150,
      "max_score": 61.89486875016836,
      "measured_at": null,
      "min_score": 12.425400361217248,
      "model_code_failure_rate": 0.4444444444444444,
      "model_code_failures": 4,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.5555555555555556,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 79,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 424,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.4738225118065,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 5,
      "repaired_rate": 0.5555555555555556,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 29.774972792271555,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 112
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 576,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 78,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0149315,
        "mean": 0.0101355,
        "median": 0.010566625,
        "min": 0.00402875,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.08108399999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.650057773456513,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 141,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:18:42Z",
      "losses": 284,
      "max_score": 45.60739618718008,
      "measured_at": null,
      "min_score": 0.5096881306947669,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 80,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 574,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.1129772607048,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 29.453697554840808,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 149
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 572,
      "canonical_public_row_identity": "publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00408087,
        "mean": 0.0022664345375,
        "median": 0.0017928150000000001,
        "min": 0.0013289177,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.0181314763
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.234451879974593,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 226,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:23:15Z",
      "losses": 224,
      "max_score": 44.17279269378332,
      "measured_at": null,
      "min_score": 19.782102062746848,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 81,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 572,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.7074437784765,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 29.24180070913258,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 427,
      "canonical_public_row_identity": "publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 69,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.11219570000000001,
        "mean": 0.0607572625,
        "median": 0.060057275,
        "min": 0.02174195,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.48605809999999994
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.74111651500159,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 71,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:50:20Z",
      "losses": 222,
      "max_score": 46.55383945263552,
      "measured_at": null,
      "min_score": 9.651433101795904,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.625,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 82,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 427,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.9232483701905,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 29.11142668015633,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 1711,
      "canonical_public_row_identity": "publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 270,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0068074,
        "mean": 0.0034371900000000006,
        "median": 0.00326368,
        "min": 0.00211404,
        "recorded_attempt_count": 35,
        "run_count": 14,
        "total": 0.04917796
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 30.09277970422465,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 691,
      "eligibility_flag": true,
      "entry_count": 11,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-07"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T03:23:43Z",
      "losses": 709,
      "max_score": 39.37852779468735,
      "measured_at": null,
      "min_score": 21.375448760554548,
      "model_code_failure_rate": 0.21428571428571427,
      "model_code_failures": 3,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": 0.7857142857142857,
      "provider": "Other",
      "provider_key": "other",
      "rank": 83,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1709,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.8687133027288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 4,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 28.332080574852135,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 309
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 658,
      "canonical_public_row_identity": "publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 88,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.09705768000000001,
        "mean": 0.0730637925,
        "median": 0.07051098,
        "min": 0.05225028,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.58451034
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.93797267122631,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 211,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:04:06Z",
      "losses": 307,
      "max_score": 47.83708028920805,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": 0.875,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 84,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 658,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.808399935368,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 7,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 27.987887233331772,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 140
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 424,
      "canonical_public_row_identity": "publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 16,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.13491350000000002,
        "mean": 0.10247140625000001,
        "median": 0.113468875,
        "min": 0.061553000000000004,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.81977125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.221768608847007,
      "contributing_entrants": null,
      "distinct_rated_opponents": 69,
      "draws": 51,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:35:20Z",
      "losses": 257,
      "max_score": 48.573486962202864,
      "measured_at": null,
      "min_score": 13.67320578769338,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": 0.625,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 85,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 424,
      "rating_method": "sequential_elo",
      "raw_elo": 1331.2285539260204,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 27.76051413105611,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 1304,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 156,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.302804525,
        "mean": 0.259828169375,
        "median": 0.2529231275,
        "min": 0.22308452,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 4.15725071
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 31.625906752195938,
      "contributing_entrants": null,
      "distinct_rated_opponents": 62,
      "draws": 396,
      "eligibility_flag": true,
      "entry_count": 9,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:56:43Z",
      "losses": 647,
      "max_score": 60.52933478522943,
      "measured_at": null,
      "min_score": 15.649250107241665,
      "model_code_failure_rate": 0.4375,
      "model_code_failures": 7,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.5625,
      "provider": "Other",
      "provider_key": "other",
      "rank": 86,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1302,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.7229374611607,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 27.38883866511949,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 259
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 2061,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 296,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 48
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0481474,
        "mean": 0.03800683125,
        "median": 0.037386975,
        "min": 0.02957195,
        "recorded_attempt_count": 48,
        "run_count": 16,
        "total": 0.6081093000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.967008360684986,
      "contributing_entrants": null,
      "distinct_rated_opponents": 97,
      "draws": 680,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:23:52Z",
      "losses": 995,
      "max_score": 40.402427775346794,
      "measured_at": null,
      "min_score": 14.602532202469558,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 87,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2052,
      "rating_method": "sequential_elo",
      "raw_elo": 1326.5708080896873,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 27.048801419001688,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 377
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 1210,
      "canonical_public_row_identity": "publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 339,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 40
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 40,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 28.744961396455825,
      "contributing_entrants": null,
      "distinct_rated_opponents": 86,
      "draws": 607,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-07"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:59Z",
      "losses": 408,
      "max_score": 40.59443860612531,
      "measured_at": null,
      "min_score": 16.708450302583884,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 6,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": 0.625,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 88,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1206,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.7257065197282,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 25.558286496840537,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 507,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 25,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0154064,
        "mean": 0.00874386,
        "median": 0.0064215999999999995,
        "min": 0.00524064,
        "recorded_attempt_count": 13,
        "run_count": 9,
        "total": 0.08145696000000001
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 27.93935400151837,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 160,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.4444444444444444,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:19:33Z",
      "losses": 235,
      "max_score": 48.468260024253375,
      "measured_at": null,
      "min_score": 3.600933227553536,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 3,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": 0.6666666666666666,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 89,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 505,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.6872091475514,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 25.246056255336732,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 110
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 689,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 28,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0057713,
        "mean": 0.004598475,
        "median": 0.0045067,
        "min": 0.0040101,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.0367878
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 20.481562275645565,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 187,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:40:55Z",
      "losses": 414,
      "max_score": 37.05506647400019,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 90,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 689,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.7762312967425,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 20.481562275645565,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 346,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 24,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.00870475,
        "mean": 0.005883593750000001,
        "median": 0.006313125,
        "min": 0.003432,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.04706874999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 18.361836436012375,
      "contributing_entrants": null,
      "distinct_rated_opponents": 66,
      "draws": 80,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T03:34:49Z",
      "losses": 200,
      "max_score": 41.31086220995625,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.625,
      "provider": "Google",
      "provider_key": "google",
      "rank": 91,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 346,
      "rating_method": "sequential_elo",
      "raw_elo": 1248.4031660913797,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 16.326237832331643,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1094,
      "canonical_public_row_identity": "publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 126,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.0032939400000000004,
        "mean": 0.0016413085000000001,
        "median": 0.0014119655,
        "min": 0.00045831,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.013130468
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 15.021272069324533,
      "contributing_entrants": null,
      "distinct_rated_opponents": 64,
      "draws": 230,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T13:45:04Z",
      "losses": 710,
      "max_score": 25.677590362951314,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 92,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1094,
      "rating_method": "sequential_elo",
      "raw_elo": 1198.9148599375305,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 14.528096821221972,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-row.v1:mixed:z-ai-glm-5-2:7c1742483386cdf8",
      "capped_draws": 18,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 1,
        "cost_basis_counts": {
          "provider_reported": 7
        },
        "evidence_basis": "Provider-reported",
        "max": 0.09063263032999999,
        "mean": 0.09063263032999999,
        "median": 0.09063263032999999,
        "min": 0.09063263032999999,
        "recorded_attempt_count": 7,
        "run_count": 2,
        "total": 0.18126526065999998
      },
      "codegen_evaluated_cells": 2,
      "conditional_success_score": 53.3313100517875,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": 2,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 2,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T14:35:20Z",
      "losses": 64,
      "max_score": 53.3313100517875,
      "measured_at": null,
      "min_score": 53.3313100517875,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.306297413937,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 53.3313100517875,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1276,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 65,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.244315,
        "mean": 0.178065,
        "median": 0.19681749999999998,
        "min": 0.10277,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.4245200000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.33568653113013,
      "contributing_entrants": null,
      "distinct_rated_opponents": 80,
      "draws": 324,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-21T15:41:46Z",
      "losses": 389,
      "max_score": 84.27791783076424,
      "measured_at": null,
      "min_score": 22.36064210907722,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1275,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.9183033568816,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 52.33568653113013,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 562
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-row.v1:mixed:meta-muse-spark-1-2:c4024993f2e98d89",
      "capped_draws": 11,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 2,
        "cost_basis_counts": {
          "provider_reported": 2
        },
        "evidence_basis": "Provider-reported",
        "max": 0.143734,
        "mean": 0.123945875,
        "median": 0.123945875,
        "min": 0.10415775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 2
        },
        "recorded_attempt_count": 2,
        "run_count": 2,
        "total": 0.24789175
      },
      "codegen_evaluated_cells": 2,
      "conditional_success_score": 51.99337133367074,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": 2,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 2,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-21T11:42:50Z",
      "losses": 70,
      "max_score": 53.346963426005594,
      "measured_at": null,
      "min_score": 50.63977924133589,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.9666145030803,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 51.99337133367074,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 714,
      "canonical_public_row_identity": "publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 19,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.6279041999999999,
        "mean": 0.526117125,
        "median": 0.5491332,
        "min": 0.330054,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 15
        },
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 4.208937000000001
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 53.2059313724767,
      "contributing_entrants": null,
      "distinct_rated_opponents": 61,
      "draws": 219,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-05",
        "GB2-06"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.14285714285714285,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T13:52:12Z",
      "losses": 173,
      "max_score": 80.95493130171027,
      "measured_at": null,
      "min_score": 23.78419992194771,
      "model_code_failure_rate": 0.2857142857142857,
      "model_code_failures": 2,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 0.7142857142857143,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 714,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.963152062793,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 4,
      "repaired_rate": 0.5714285714285714,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 48.91342129541595,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 322
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 17
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.30059250000000004,
        "mean": 0.256004375,
        "median": 0.25514000000000003,
        "min": 0.2090225,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 17
        },
        "run_count": 16,
        "token_priced_attempt_count": 17,
        "total": 4.09607
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 46.47662546307069,
      "contributing_entrants": null,
      "distinct_rated_opponents": 76,
      "draws": 337,
      "eligibility_flag": false,
      "entry_count": 15,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T20:23:03Z",
      "losses": 305,
      "max_score": 61.677366694707196,
      "measured_at": null,
      "min_score": 21.53151391139788,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 0.9375,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 964,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.8802833421396,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 45.73275943329751,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 322
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 337,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 10,
      "codegen_cost_usd": {
        "admitted_cell_count": 25,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 31
        },
        "evidence_basis": "Provider-reported",
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 31,
        "run_count": 28,
        "total": 0.0
      },
      "codegen_evaluated_cells": 25,
      "conditional_success_score": 44.31643372112509,
      "contributing_entrants": null,
      "distinct_rated_opponents": 3,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 22,
      "first_pass_rate": 0.88,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "infra_failures_excluded": 5,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T15:12:59Z",
      "losses": 81,
      "max_score": 52.06957808560736,
      "measured_at": null,
      "min_score": 35.26149604339514,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 333,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.5303719528426,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 3,
      "repaired_rate": 0.12,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 44.31643372112509,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 191
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1256,
      "canonical_public_row_identity": "publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 125,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.73533,
        "mean": 0.5886581249999999,
        "median": 0.58241,
        "min": 0.410635,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.709265
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.019970128414535,
      "contributing_entrants": null,
      "distinct_rated_opponents": 65,
      "draws": 351,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T04:11:45Z",
      "losses": 447,
      "max_score": 65.20264997974215,
      "measured_at": null,
      "min_score": 13.078411737521655,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1256,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.5947734548254,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 43.019970128414535,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 458
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 464,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 66,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.2996388,
        "mean": 0.13471628689999998,
        "median": 0.1144847257,
        "min": 0.027613287599999998,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 1.0777302952
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.17892461527247,
      "contributing_entrants": null,
      "distinct_rated_opponents": 70,
      "draws": 110,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:01Z",
      "losses": 186,
      "max_score": 68.98589007065465,
      "measured_at": null,
      "min_score": 31.43712263783562,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": 0.75,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 464,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.9451099086941,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.974331635082116,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 168
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 129,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 12,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.40721066666666667,
        "mean": 0.3468699583333334,
        "median": 0.3476285,
        "min": 0.237408,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 13,
        "total": 4.659586
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 44.78487833740139,
      "contributing_entrants": null,
      "distinct_rated_opponents": 23,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.8,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-08"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:51:05Z",
      "losses": 29,
      "max_score": 68.66906686669674,
      "measured_at": null,
      "min_score": 20.752949450340513,
      "model_code_failure_rate": 0.2,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": 0.8,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 129,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.0316185236172,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.35492289782546,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 11,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "evidence_basis": "Provider-reported",
        "max": 0.25803,
        "mean": 0.104435,
        "median": 0.081263,
        "min": 0.075542,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.83548
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.089605395034724,
      "contributing_entrants": null,
      "distinct_rated_opponents": 27,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T05:21:47Z",
      "losses": 41,
      "max_score": 55.331168423892514,
      "measured_at": null,
      "min_score": 11.831462426203206,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.0240200539204,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 40.089605395034724,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-row.v1:mixed:gpt-4-1-nano:68d5f0be3c90fb50",
      "capped_draws": 35,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 1,
        "cost_basis_counts": {
          "estimated": 1,
          "local_standard_estimate": 1
        },
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "max": 0.0023425,
        "mean": 0.0023425,
        "median": 0.0023425,
        "min": 0.0023425,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 1,
          "boardgame-list-prices-2026-08-08": 1
        },
        "recorded_attempt_count": 1,
        "run_count": 1,
        "token_priced_attempt_count": 1,
        "total": 0.0023425
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": 39.72974279439747,
      "contributing_entrants": null,
      "distinct_rated_opponents": 49,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": 1,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1-nano",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 1,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-14T22:12:59Z",
      "losses": 67,
      "max_score": 39.72974279439747,
      "measured_at": null,
      "min_score": 39.72974279439747,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.5094730893666,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Reasoning field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 39.72974279439747,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 504,
      "canonical_public_row_identity": "publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 33,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.1311545862,
        "mean": 0.02955606902857143,
        "median": 0.0063034062,
        "min": 0.0057139812,
        "recorded_attempt_count": 10,
        "run_count": 7,
        "total": 0.2068924832
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 40.66399209647054,
      "contributing_entrants": null,
      "distinct_rated_opponents": 66,
      "draws": 122,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5714285714285714,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:19:05Z",
      "losses": 183,
      "max_score": 52.982816468950794,
      "measured_at": null,
      "min_score": 25.444968645038077,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 1,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 504,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.5531363843736,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 39.12670850733229,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 394,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemma-4-31b-it:8d94257f5348b920",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0092087,
        "mean": 0.006571171428571429,
        "median": 0.00666192,
        "min": 0.00456754,
        "recorded_attempt_count": 15,
        "run_count": 7,
        "total": 0.0459982
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 43.751461488092524,
      "contributing_entrants": null,
      "distinct_rated_opponents": 65,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-01"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:57:18Z",
      "losses": 171,
      "max_score": 59.53630433773744,
      "measured_at": null,
      "min_score": 37.24500604167221,
      "model_code_failure_rate": 0.42857142857142855,
      "model_code_failures": 3,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": 0.5714285714285714,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 392,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.1502970457286,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 4,
      "repaired_rate": 0.5714285714285714,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 38.039346973942585,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 155
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 117,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 17,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.06806129999999999,
        "mean": 0.037113121874999995,
        "median": 0.0310111,
        "min": 0.0230335,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 10,
        "total": 0.38761484999999996
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 37.264078008031774,
      "contributing_entrants": null,
      "distinct_rated_opponents": 24,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.6,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T03:04:42Z",
      "losses": 33,
      "max_score": 55.386274611099374,
      "measured_at": null,
      "min_score": 11.59827459432436,
      "model_code_failure_rate": 0.2,
      "model_code_failures": 2,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": 0.8,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 117,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.153234157907,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.2,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 35.24218909333583,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 16,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "evidence_basis": "Provider-reported",
        "max": 0.173358,
        "mean": 0.1197105,
        "median": 0.119348,
        "min": 0.066054,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.9576840000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.749029621979645,
      "contributing_entrants": null,
      "distinct_rated_opponents": 23,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T02:23:52Z",
      "losses": 45,
      "max_score": 65.33787445900813,
      "measured_at": null,
      "min_score": 7.529917385447114,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.251651276839,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.749029621979645,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": 309,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 21,
      "codegen_cost_usd": {
        "admitted_cell_count": 26,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 39,
        "run_count": 30,
        "total": 0.0
      },
      "codegen_evaluated_cells": 30,
      "conditional_success_score": 35.15050484430993,
      "contributing_entrants": null,
      "distinct_rated_opponents": 3,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": 21,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-06"
      ],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.7,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T14:12:11Z",
      "losses": 133,
      "max_score": 42.84271453304636,
      "measured_at": null,
      "min_score": 10.044999300170076,
      "model_code_failure_rate": 0.13333333333333333,
      "model_code_failures": 4,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": 0.8666666666666667,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.884848536596,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 5,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 33.91521622287523,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-row.v1:mixed:stepfun-step-3-7-flash:dfa24619f0407197",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0711619,
        "mean": 0.039345212500000004,
        "median": 0.033877925,
        "min": 0.02387735,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.31476170000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.412835389657154,
      "contributing_entrants": null,
      "distinct_rated_opponents": 66,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:10Z",
      "losses": 139,
      "max_score": 51.477038427166434,
      "measured_at": null,
      "min_score": 23.01907317579323,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.5,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.29805301024,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 32.301215578893725,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 141,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.014791950000000002,
        "mean": 0.007616140625,
        "median": 0.005694875,
        "min": 0.00430875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.07206399999999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 32.851444464888665,
      "contributing_entrants": null,
      "distinct_rated_opponents": 28,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.5555555555555556,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:13:39Z",
      "losses": 61,
      "max_score": 42.18481948599077,
      "measured_at": null,
      "min_score": 15.033187607000485,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 141,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.932625654153,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 3,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.898211952807085,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 15,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.01196465,
        "mean": 0.00854730625,
        "median": 0.008640199999999999,
        "min": 0.00555765,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 15
        },
        "recorded_attempt_count": 15,
        "run_count": 9,
        "total": 0.07763974999999998
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 32.80838268685741,
      "contributing_entrants": null,
      "distinct_rated_opponents": 26,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.4444444444444444,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:02:59Z",
      "losses": 62,
      "max_score": 47.504378523447755,
      "measured_at": null,
      "min_score": 14.229198182783765,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.721214854816,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 4,
      "repaired_rate": 0.4444444444444444,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.856399674988566,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 576,
      "canonical_public_row_identity": "publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 93,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 36
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.215758025,
        "mean": 0.16162675,
        "median": 0.1594081875,
        "min": 0.098579625,
        "recorded_attempt_count": 36,
        "run_count": 16,
        "total": 2.5860279999999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 38.57817288064592,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 261,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:41:06Z",
      "losses": 174,
      "max_score": 63.528190114310334,
      "measured_at": null,
      "min_score": 16.61661173350593,
      "model_code_failure_rate": 0.5625,
      "model_code_failures": 9,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": 0.4375,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 576,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.545103745422,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.375175900391902,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 560,
      "canonical_public_row_identity": "publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 105,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00391754,
        "mean": 0.0023617857142857143,
        "median": 0.00186618,
        "min": 0.00144036,
        "recorded_attempt_count": 8,
        "run_count": 7,
        "total": 0.016532500000000002
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 32.366653836465424,
      "contributing_entrants": null,
      "distinct_rated_opponents": 71,
      "draws": 168,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.7142857142857143,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:48:11Z",
      "losses": 235,
      "max_score": 44.033324039853156,
      "measured_at": null,
      "min_score": 18.568992620174647,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 1,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 558,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.5759456811306,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.14285714285714285,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.14304731844145,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 155
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 634,
      "canonical_public_row_identity": "publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 99,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.03772852,
        "mean": 0.024905897500000003,
        "median": 0.026095300000000002,
        "min": 0.00984735,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.19924718
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.916379646070055,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 110,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T10:07:05Z",
      "losses": 321,
      "max_score": 52.921447482930446,
      "measured_at": null,
      "min_score": 22.799140452263753,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.5,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 630,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.0519781417674,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.0428513085255,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-row.v1:mixed:mistralai-mistral-medium-3-5:6deb1b60bb205df7",
      "capped_draws": 96,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.06200699999999999,
        "mean": 0.042994687499999996,
        "median": 0.0423105,
        "min": 0.0223935,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.34395749999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.54412660468169,
      "contributing_entrants": null,
      "distinct_rated_opponents": 69,
      "draws": 104,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:49:34Z",
      "losses": 155,
      "max_score": 40.86555647776021,
      "measured_at": null,
      "min_score": 30.076430145642476,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": 0.5,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 376,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.894700456406,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 30.729825060454733,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 20,
      "wins": 117
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 15,
      "codegen_cost_usd": {
        "admitted_cell_count": 28,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 42
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 42,
        "run_count": 30,
        "total": 0.0
      },
      "codegen_evaluated_cells": 30,
      "conditional_success_score": 31.110992060585442,
      "contributing_entrants": null,
      "distinct_rated_opponents": 3,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": 22,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.6333333333333333,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T15:12:59Z",
      "losses": 155,
      "max_score": 45.08609625332008,
      "measured_at": null,
      "min_score": 3.8514807674763087,
      "model_code_failure_rate": 0.06666666666666667,
      "model_code_failures": 2,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": 0.9333333333333333,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 321,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.0019137585691,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 9,
      "repaired_rate": 0.3,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 30.57898417462382,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 83
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 793,
      "canonical_public_row_identity": "publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 126,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 10,
        "max": 0.11839474,
        "mean": 0.07845433000000002,
        "median": 0.08046371000000001,
        "min": 0.036046930000000005,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 1.25526928
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 31.522734372110563,
      "contributing_entrants": null,
      "distinct_rated_opponents": 86,
      "draws": 237,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T12:49:16Z",
      "losses": 384,
      "max_score": 57.38467373838492,
      "measured_at": null,
      "min_score": 6.641760874582254,
      "model_code_failure_rate": 0.625,
      "model_code_failures": 10,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.375,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 793,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.4665087257963,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 24.66787274376822,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 639,
      "canonical_public_row_identity": "publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 147,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 8,
          "local_standard_estimate": 13
        },
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.17217,
        "mean": 0.11039474999999999,
        "median": 0.10846,
        "min": 0.07562,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 13,
          "boardgame-list-prices-2026-08-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 0.8831579999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 27.169386199575268,
      "contributing_entrants": null,
      "distinct_rated_opponents": 63,
      "draws": 172,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:51:52Z",
      "losses": 351,
      "max_score": 53.99459166857962,
      "measured_at": null,
      "min_score": 2.8219078055756306,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.5,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 639,
      "rating_method": "sequential_elo",
      "raw_elo": 1285.213375239646,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 22.846639459866584,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 52
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 52,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": 27.4134235117906,
      "contributing_entrants": null,
      "distinct_rated_opponents": 73,
      "draws": 254,
      "eligibility_flag": false,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.06666666666666667,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold",
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T10:20:46Z",
      "losses": 493,
      "max_score": 43.039137688291845,
      "measured_at": null,
      "min_score": 13.028496075357975,
      "model_code_failure_rate": 0.6,
      "model_code_failures": 9,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": 0.4,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 974,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.342805247122,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": 5,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 21.801093294221513,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 227
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 496,
      "canonical_public_row_identity": "publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 182,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 30,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.306622154385593,
      "contributing_entrants": null,
      "distinct_rated_opponents": 72,
      "draws": 182,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.1875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:09:16Z",
      "losses": 232,
      "max_score": 33.85875457644092,
      "measured_at": null,
      "min_score": 23.179971665322682,
      "model_code_failure_rate": 0.6875,
      "model_code_failures": 11,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": 0.3125,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.214856005476,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": 2,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 20.41646207891444,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 78
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-row.v1:mixed:mistralai-mistral-medium-3-5:54288de170df8ebb",
      "capped_draws": 17,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.3927285,
        "mean": 0.1902770625,
        "median": 0.16804049999999998,
        "min": 0.08751,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 1.914945
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 21.756661652782977,
      "contributing_entrants": null,
      "distinct_rated_opponents": 57,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.2222222222222222,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:22:40Z",
      "losses": 226,
      "max_score": 31.129646707507366,
      "measured_at": null,
      "min_score": 11.636247230495337,
      "model_code_failure_rate": 0.5555555555555556,
      "model_code_failures": 5,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": 0.4444444444444444,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1224.5730997935657,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 17.76423985189867,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-19T23:51:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 2032.611031916279,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-20T02:25:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1984.8430422639274,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 95.06137796160141,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1889.6728264013168,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 84.5317048418163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1838.9026372811668,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 81.00202184525405,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1843.9420024778738,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 80.39863746617029,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-20T01:48:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1837.8230227206066,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 79.71591004614217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-19T22:28:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1827.927379066235,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 78.74292256811869,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-03T18:34:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1798.3560336460778,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 75.63550927040828,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 2,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-04T22:26:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.6986255095305,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 74.5791609476971,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-19T23:52:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1772.7929800733582,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 73.18339250918713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-05T05:08:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1773.8960199591977,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.88756496655336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-22T09:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1751.5204705553888,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 70.89182828429095,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T02:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1751.7035828845744,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 70.59314019339122,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-03T18:12:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.7718654981127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 69.68374424625355,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 2,
      "wins": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 87,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1733.9815154005573,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.96857780411901,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.993443214731016,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1716.4746501562718,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.61223768430166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.902777777777777,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 139,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-20T02:13:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1704.7601387652967,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 66.80663569310781,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 204,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 92,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-05T05:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 203,
      "rating_method": "sequential_elo",
      "raw_elo": 1702.542944257067,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 66.07679415920771,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.658091940411904,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 143,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-19T23:48:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 143,
      "rating_method": "sequential_elo",
      "raw_elo": 1687.8947917300393,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 65.20264997974215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 91,
      "rating_method": "sequential_elo",
      "raw_elo": 1678.161582569883,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.331047607164344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.378603514268699,
      "unilateral_faults": 1,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-19T23:39:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.03180370545,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.721626572263794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-19T23:37:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.0651074364548,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.974479549744906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-31T02:19:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.4221322011101,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.386461607802104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.9301421808211,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.87170060837425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.442124593186,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.10237984120693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 50,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-03T14:42:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.152563313432,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.28936991672205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.0733020497882,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-03T16:16:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.9382025233147,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.26867546532442,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 2,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-03T13:20:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.1676828791458,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.3619117116447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 45,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-19T23:49:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.458566001231,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.02925130550037,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-22T14:45:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.069646677,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.83944130802511,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 86,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-05T05:01:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.1217179945165,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.113615016738166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.340523799551441,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 418,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 157,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 151,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 418,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.7594820788852,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.03900598894137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.20594182360189764,
      "unilateral_faults": 0,
      "wins": 235
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-31T01:07:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.7687032819815,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.548619261546875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-08-05T03:05:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.2703740811967,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.857347305850986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-2:c4024993f2e98d89",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-20T02:02:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.2892427440295,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.346963426005594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.9122301422362,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.04366523994301,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 89,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-20T02:03:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 89,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.7387010272973,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.24671194156034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.954627669472988,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-31T03:24:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.6015315816996,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.92333504583319,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 303,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 92,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-08-22T09:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.1126584018375,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.06934497191142,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 107
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 84,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.1824746630828,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.52153198061598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-03T12:31:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.0962511352168,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.32288377460864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-05T01:58:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.9099785297988,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.80330844143976,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 101,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.667219495499,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.51241566794083,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.854879649062207,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 191,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 130,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 130,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-20T02:03:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 191,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.1217619645342,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.250941248501725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 85,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-07-31T03:00:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.529748830355,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.15114198242796,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.30098989141123,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-04T20:42:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.6558361046946,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.96146347343779,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 197,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 126,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 126,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-23T09:56:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 197,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.9335994737546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.760117376536684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-08-03T09:57:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.8769477318842,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.75703593114919,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-03T02:39:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.0881129608072,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.6769093213218,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-03T14:29:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.8516420385984,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.549073450674925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-03T14:22:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.2412310238194,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.395710077391875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.2629278529,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.19117788523471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-05T03:13:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.7710394884484,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.033324039853156,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.2955239513867,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.91721529100322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-03T14:21:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.1750231054355,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.773386925532954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-05T04:18:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.983885430028,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.640363221816266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 87,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-23T12:40:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 87,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.2271709641848,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.183715862077705,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.550179088902606,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-23T12:28:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.8930518724999,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.77290160209612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-23T12:28:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.420159897876,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.69013350806352,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.937234683748,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.41290592375142,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-05T02:21:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.0985357998015,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.208769238182654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-31T01:08:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.6116867747367,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.118148020938065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 85,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-19T03:12:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 85,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.5112502726618,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.887590399986145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.16638660171921,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:mistralai-mistral-medium-3-5:6deb1b60bb205df7",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:10:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.7788681959753,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.86555647776021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 20,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 352,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 137,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 149,
      "max_score": null,
      "measured_at": "2026-08-22T19:58:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.289152623251,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.402427775346794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.1253265344149,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.3121483931683,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-4-1-nano:68d5f0be3c90fb50",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1-nano",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-14T22:12:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.5094730893666,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Reasoning field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.72974279439747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-22T09:27:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.182936178097,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.68437234670113,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-22T16:31:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.6122502478056,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.66966887583633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-08-22T19:58:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.1200705128342,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.37852779468735,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-05T04:12:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.8660097244824,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.24390988896453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-31T02:06:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.1483095867432,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.18284182983124,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.4270688693366,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.80076732863321,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 294,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "draws": 95,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 294,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.6441048464835,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.99825914849188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.7059748335482,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.856998866883636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 130,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 157,
      "max_score": null,
      "measured_at": "2026-08-22T14:46:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.6662439845072,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.62677721692003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 78,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.391363495254,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.634762539218215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.706222621085206,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 65,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-07-31T02:19:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.2125499308513,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.46949800381537,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.23082238610738,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-08-05T05:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.9183970053725,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.44482183373839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-23T12:17:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.826841528916,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.220512032278116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-08-15T02:21:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.0621525194288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.17571462476984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-04T23:53:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.7043878093432,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.14530790884301,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1376.434958978076,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.11260422145595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 88,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1366.913746675928,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.839508997521932,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.154975300928378,
      "unilateral_faults": null,
      "wins": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 74,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-07-31T03:20:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.590696843264,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.68527547982116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.046738977996931,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.9468682572074,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.004907598248348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-04T23:49:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.725824672585,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.47909111397539,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-08-05T02:21:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.6106318223515,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.18114898717137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-22T07:23:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.2484890428086,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.4679471098268,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.83081881614,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.776223890208286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1297.8379592305182,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.206848131834946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 96,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 96,
      "draws": 96,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1287.6381095392642,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.179971665322682,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.667409425864287,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 126,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 183,
      "max_score": null,
      "measured_at": "2026-08-22T16:31:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.0173148882393,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.875190223871893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:11:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.7786038469053,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.501856921354634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 15,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-08-20T01:50:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1255.2978439767162,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.281722008614956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.463945712701573,
      "unilateral_faults": null,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 89,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-23T12:40:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 89,
      "rating_method": "sequential_elo",
      "raw_elo": 1239.5383535693904,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.93516275734703,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.954627669472988,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-08-22T09:27:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1226.334134979911,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.729065008395047,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-31T00:39:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1238.9848297340284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.329198413600206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-08-23T09:56:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1209.1921036226092,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 15.649250107241665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1214.7994373479398,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 15.302941621960535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 82,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-08-05T03:22:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1214.2842678515308,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 15.136633992883711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.22239302669203,
      "unilateral_faults": 2,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 79,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 105,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 122,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1183.164429430121,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 12.558196600852206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.4969716034024056,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:mistralai-mistral-medium-3-5:54288de170df8ebb",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1182.0336827681099,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 11.636247230495337,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-31T03:26:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1168.6771765022436,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 10.192924369283574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1164.068130786268,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 9.651433101795904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-08-20T02:24:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1082.9163024850677,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 2.8219078055756306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-23T09:27:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1830.0318043667605,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-05T02:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1737.894247067,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 79.43336636141659,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-05T01:25:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1707.3717186637177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.77270456368558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-04T08:44:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1694.6686240486547,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.36660657293471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.98404749947013,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-04T02:44:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1673.7931137310256,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 64.79913198095714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 2,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-03T12:23:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1668.274080690368,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.392777513578906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 75,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.9382682376422,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.97608367109741,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.60765757439077,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 40,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1626.3155963816746,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 54.52715766883468,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-23T09:27:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.5705707988113,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.06793491447559,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T02:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.1507466448422,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.85138391276626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-03T09:39:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.48401992745,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.26540457323291,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-23T14:10:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.1315475505453,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.26149604339514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-23T06:52:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.6444248483235,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.110695747971825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 67,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-19T23:36:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 67,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.022713465008,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.93634004616261,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.883906259083243,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-15T01:46:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.7378064158515,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.897713502544164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-05T01:51:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.26315875289,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.236124905450517,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-02T23:10:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.3810335953954,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.15047326894219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 107,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-23T03:23:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.1866099898193,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.69898854487774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.5178730212592662,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-15T01:45:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.1681603311224,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.25129104934696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-23T03:03:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.8831773296815,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.127464596852075,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-22T08:14:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.869141070355,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.812606919993172,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-03T01:05:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.2755505440737,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.743400089025748,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-04T21:44:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.3332105179659,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.56425672722357,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 77,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-19T21:54:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 77,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.2440690369426,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.90894221037543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.86385170722978,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-03T08:48:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.3456741149573,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.444968645038077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-03T04:42:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.2427797755156,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.173568805236624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-04T20:03:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.9557794402522,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.982247392476896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-03T10:38:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.0520433424101,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.79810278001538,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-31T01:21:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.1338632198867,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.338864125825364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.2026519480598,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.312887404123998,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-15T01:43:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.559288564265,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.109111227556788,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 106,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-15T01:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.5010269282043,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.78419992194771,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.9100862300777,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.435946683398193,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:stepfun-step-3-7-flash:dfa24619f0407197",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-03T09:30:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.1945310202682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.01907317579323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 130,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-19T23:37:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.3717066027084,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.928875872336782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 105,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 103,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-22T08:45:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 105,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.5153667728528,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.719387636610737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.8142931178632065,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.2479095839017,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.584554928424122,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-19T21:55:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.0049313514542,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.36064210907722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 70,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-03T15:08:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.703775598533,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.057846645260756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-03T10:43:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.1788100994386,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.8994809309449,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-03T12:16:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.896463396586,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.89947442115403,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-03T12:16:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.9758894809659,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.895370370120215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-03T12:15:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.2560006314968,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.69349452538362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.8595823514117,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.54178243508168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 108,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-31T03:33:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.4403366454433,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.53151391139788,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.37252890985009,
      "unilateral_faults": null,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.2648473381566,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.497354945210386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "draws": 223,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-23T03:23:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.6231620188373,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.375448760554548,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-05T02:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.566214509699,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.8256604365787,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-23T05:29:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.1352852847508,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.752949450340513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-04T22:55:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.7375666323005,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.5446273273821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-22T07:54:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.1282589545453,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.275423642118344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 132,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-31T01:17:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.3565115110625,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.224561007386125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.836607386351783,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 109,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.0862907777541,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.20918702880969,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-03T08:04:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.2427790750996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.976294071045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.498417326438,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.821595384418693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-05T00:29:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.3214890914899,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.782102062746848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-31T02:24:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.3532370944224,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.75239474357151,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "draws": 226,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-22T08:45:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.9746151933264,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.712695556979902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.975653602088653,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 56,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-04T08:44:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.6046613504113,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.686387180079826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.910536671832062,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-03T03:19:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.43993039221,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.68138864924798,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 77,
      "draws": 139,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.1081705185377,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.627918979635304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.867341638060083,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-04T23:05:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.431303811449,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.58339791797017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.0127959450965,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.31198981966688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.9086495306929,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.216835075427902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-05T02:59:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.1326032111256,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.14734246410184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 85,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:26:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.934365357052,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.00038445855571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.030300912858,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.901290276570073,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-23T06:52:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.5824743341007,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.648854275319852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 57,
      "draws": 108,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.457526624261,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.537461190466654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.910536671832062,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-22T07:54:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.9158431127426,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.905822221963863,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 91,
      "draws": 223,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-23T03:03:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.93655147432,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.43890191914832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.1611854626755758,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-03T04:41:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.4123886391003,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.398846802778316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 58,
      "draws": 100,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.919888631724,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.951008971108347,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.37252890985009,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-19T21:57:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.9484790906874,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.944819699504418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 100,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-05T04:27:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.0482654162681,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.708450302583884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-05T04:32:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.9080120948634,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.61661173350593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.2399661529485,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.460871449147128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.7870290620301,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.174375669656794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-03T05:47:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.9211674035894,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 15.975113871358344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.996408990712,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 15.033187607000485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-20T02:43:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.2519536138268,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 14.67781433099459,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 11,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-23T00:33:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.9154364994188,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 14.229198182783765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-03T14:23:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.1637680119986,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 13.814065400064843,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-04T05:07:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.1010532318462,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 13.456150792860978,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 2,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-31T02:27:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.9854646078195,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 13.368124963630589,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-19T22:29:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.5395963112296,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 13.078411737521655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 9,
      "draws": 95,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-19T21:57:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.0330816696924,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 13.028496075357975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 38.47986322289016,
      "unilateral_faults": null,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.173692393705,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 11.831462426203206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.8561157275458,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 11.59827459432436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.162820902962,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 10.044999300170076,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-03T08:16:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.731839146371,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 9.522795772569406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-22T08:45:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.8967197535371,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 7.529917385447114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.4161473966744,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 3.8514807674763087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-21T15:52:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1873.3759975611176,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-03T14:17:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1837.3301063724912,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 92.59586913113255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-05T04:20:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1810.7920166159938,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 90.23843179247481,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.888824360518605,
      "unilateral_faults": 0,
      "wins": 112
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.8727510068502,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 86.9870467732465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-21T11:42:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1643.4933772800982,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.46351429427254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-03T06:16:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1659.0010157114255,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.5967962093199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.678571428571434,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-08-21T15:52:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.1519271610578,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.15840316174446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 73,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.1626741002503,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.81837924586282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.377800258513929,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-03T14:16:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.7752708410653,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.693530462272456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-21T05:32:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.2383618839162,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.06942397101405,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.0346949443713,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.66426066452565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-08-22T12:02:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.2792867639394,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.38467373838492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-15T02:26:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.1523284131163,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.13966476484938,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1568.0355049211498,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.34552410919058,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 92,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 92,
      "max_score": null,
      "measured_at": "2026-08-22T20:25:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.8864018616787,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 54.3795837338173,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.042462425705284,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.5926549807855,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 54.16096619535128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-21T11:43:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.6194374124107,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.664178268995066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:7c1742483386cdf8",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.306297413937,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.3313100517875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.9042490427370184,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-23T02:31:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.3820976110903,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.28442509273992,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-22T20:29:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.6522566987526,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.72856933942535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.6746024305037,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.97927682744617,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "draws": 98,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.994876963442,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.88685308179679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meta-muse-spark-1-2:c4024993f2e98d89",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-21T11:42:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.6439862621312,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.63977924133589,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 69,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-08-03T14:17:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.1530595800598,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.69220134120665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-21T04:34:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.1018206087042,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.23562494881364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.0178075202837,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.047889752679794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 101,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.6464217020275,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.783597464425156,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.2220869120796065,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.9851115234762,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.4984550891471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.1972496241688,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.28468874615239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.213976730923585,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-05T05:42:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.5686533652022,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.956517411641435,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-03T13:39:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.0571494972528,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.6580131540409,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:55:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.233407603528,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.12212623530856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-03T12:18:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.0287857501219,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.64591903633767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.6816547576702,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.57541663713608,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-31T02:50:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.2149280033655,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.206404703543946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-21T09:13:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.5878420683082,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.093217679579666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": null,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-07-31T01:23:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 46,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.4689000736262,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.769924095864134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": null,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.899175382564,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.14726180448418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-05T04:03:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.862249672601,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.819799277453555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.3068886929552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.78614708777877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 73,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 40,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 73,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.5678575239842,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.7743274862355,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.373819371909642,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-22T12:02:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.74320418467,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.671930557268624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 25,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-23T14:10:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 24,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.4080832752197,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.84271453304636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 94.92504905630729,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-08-23T08:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.8365938246095,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.7632763142804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-22T21:12:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.056619582484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.74500116475145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.820909745894,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.18481948599077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 46,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-31T01:34:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.803408628788,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.12992846790356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.23208533928221,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-08-22T23:22:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.3749817413207,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.0930986190164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 48,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-23T03:05:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.1101031373976,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.56882637540658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-21T15:54:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.3734345802525,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.37834288379551,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-03T15:07:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.1792879779643,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.969815876809534,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-08-22T14:30:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.2573394100423,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.4983370246016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-05T03:54:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.8196949799096,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.43722567444062,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.9820939819956,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.34825846139262,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-05T02:49:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.812696623928,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.12729304970078,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 231,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 100,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-08-22T23:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 231,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.945798874046,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.88354454110426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.902777777777777,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-03T10:31:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.3652413928949,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.87335695062395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-23T02:31:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.9877282935317,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.667892968316686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 91,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-08-23T05:19:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 91,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.518054717542,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.36327550240593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.378603514268699,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-22T13:52:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.3742508178495,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.21229308756867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-22T21:12:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.5845812595855,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.158820258821116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-21T05:32:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.9524119202586,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.11059502696876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 271,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 116,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-08-23T08:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 271,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.6859481766683,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.88817423342006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 93,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-21T11:43:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.6598711541665,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.881693886910185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 39,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 18,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-23T15:12:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 35,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.2407303398938,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.512996050435966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 96.61669937087152,
      "unilateral_faults": 4,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-05T00:30:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.9342129195318,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.11887554806834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-03T04:31:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.7895878905797,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.09206930228779,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-03T11:59:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.8225277095194,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.548190679008606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.8471904592118,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.08306137270303,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 55,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-03T03:06:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.9628765018,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.28813655813136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 1,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 112,
      "draws": 125,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-08-23T03:05:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.4802666018688,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.33064329629842,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-04T08:55:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.0159683307136,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.28796962477342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-03T12:01:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.1877638819335,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.72802275090764,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-31T02:57:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.6979199994657,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.19952060625756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.9868138511533,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.87102615666334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.213976730923585,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-04T22:38:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.904948282172,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.740913466707504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-31T02:59:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.0125908179525,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.268010627958816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T01:53:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.2862829940107,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.9585259455821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-23T15:12:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 23,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2308212149396,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.219076953501776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 97.46252452815364,
      "unilateral_faults": 1,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.6716512399985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.68470258883002,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.29009959559265,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-21T11:43:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.3181825628085,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.125725179167283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:21:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.4114294677433,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.834909047409482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 56.49112594673751,
      "unilateral_faults": null,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 13,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-22T20:29:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 13,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.7603793686078,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.231216213725585,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 89.8806209562122,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-23T05:19:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.246671542211,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.807525230813738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-08-22T23:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1274.046932999176,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.6420903975188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 104,
      "max_score": null,
      "measured_at": "2026-08-22T17:42:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1155.0432979180157,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1867.362240038843,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-22T05:58:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1813.5063596110099,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 91.32241413921264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1805.933180290257,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 90.14837149543118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 60,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T04:13:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1756.1344548669742,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 82.0434973958146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.606750070474945,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-22T06:50:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.845435170706,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 80.95493130171027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-05T01:54:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.7791355637896,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.996358539488305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 289,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 107,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.9332057560987,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.70973443654603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 85,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-22T04:12:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1605.7836316615358,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.29009953663199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 40,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1605.3952927027833,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.87607730332684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.1701606113888,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.05592222052655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-05T03:47:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.248490406413,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.24795980739564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-05T04:04:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.9623544152807,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.05762102524152,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 40,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.6914890100186,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.06108211106203,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 87,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.2200909613516,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.33723880160861,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.552760371103872,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 82,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-05T03:54:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.25942083376,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.301004509305145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.144085005109797,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 11,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.3194324712535,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.942602650877994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.5411300031487,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.930917233328884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-05T05:04:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.6279522740244,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.89782707711206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.3585485416486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.747585899586106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-31T02:32:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.309666305548,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.87509260752541,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-23T04:48:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.264516335169,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.172469636670904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:stepfun-step-3-7-flash:dfa24619f0407197",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.768886248649,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.188981149238096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-05T02:20:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.5585709646791,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.936775078827324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "draws": 154,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-23T01:51:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.3930229925163,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.73973256856557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.1524206416837046,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-22T17:44:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.2617872617693,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.88860616405384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-05T02:15:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.0990916013604,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.844934191198654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-05T04:03:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.6460224672696,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.846681213455774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:04:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.092051220334,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.265005107407845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-22T13:00:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.857410286727,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.558687152271936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 131,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 88,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 127,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.0663571860498,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.21132135718317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.444173824159213,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.3498876524732,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.14362212889749,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 98,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-31T02:31:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.192769921518,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.04295247255884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.459772198068393,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.404650141681,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.00273303004231,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-23T12:27:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.063493316194,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.953702406627194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T03:47:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.501959438092,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.77828780767661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-04T03:46:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.7535575112174,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.723688617519116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 2,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-21T20:36:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.6521530811533,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.552941865834306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.431367332239,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.48658634194338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.6292037741962,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.29925429844576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.354766936686,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.149311285803776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-05T01:02:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.3027736844938,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.00299359107813,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.9213014671434,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.788828941639004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-31T02:31:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.504648883028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.772376702118756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 59,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.6960155718434,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.6936216942447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.96867677046422,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.6944633151002,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.59443860612531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-05T02:13:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.8875603348063,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.551305110490894,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.9572707576879,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.45363557593279,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.7935464109898,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.36325367187167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 99,
      "draws": 206,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6315748334123,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.25224242939918,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.3450286460047,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.070339654447714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-05T00:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.5305327733142,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.50807424575855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-03T14:28:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.1158867823526,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.477544864233046,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.6409821341078,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.474444158374034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-03T11:50:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.4264941488582,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.469766608891966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-05T03:15:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.5093095901468,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.31546308499324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 237,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 183,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-22T14:13:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.048880995099,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.2343034850068,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.1764504826757323,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-22T11:33:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.013285163808,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.75702900741598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.284379118747,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.75509843220986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.3430744138302,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.653128654939394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-30T18:04:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3591546604298,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.58942946961961,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 91,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-31T02:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.5655938537338,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.21256704067065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.06074898572802,
      "unilateral_faults": null,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-21T20:01:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.8932821904841,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.20889098134736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.0718049538236,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.01263971429604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemma-4-31b-it:8d94257f5348b920",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-04T02:50:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.117049186159,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.777956524978244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 2,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-22T11:33:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.7988288950792,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.42221478251373,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.707966398987,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.34375399192475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.4540362928522,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.05506647400019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-04T23:28:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.7918733909657,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.89168262273526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 239,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "draws": 172,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-21T20:33:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 239,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.8314186207444,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.87160934044171,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.0706571305287857,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-05T03:14:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.309058381632,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.81825538042852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 257,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 99,
      "draws": 163,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.4196953279754,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.70643364563969,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 28,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T01:16:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.12603505286,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.61467322762245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 29.395347377897878,
      "unilateral_faults": null,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-03T11:49:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.678974566677,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.401476747289344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 76,
      "draws": 105,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-05T03:47:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.7466794854122,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.1685979425594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.51792189268726,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 76,
      "draws": 110,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-31T02:43:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1456.7060798338593,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.13432688848033,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.493504750482622,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.207397477533,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.776619836599615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 151,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-22T04:11:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 151,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.440206836578,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.58935434104422,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-23T12:27:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.2014764650874,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.153932317419596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.127962983689,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.834147059507195,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T05:04:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.491289436351,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.75060930600307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T01:17:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.2230735526018,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.63241298761103,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-05T00:50:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.1168128216952,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.71863054561698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 127,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 91,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 127,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.7661524468779,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.63833030232732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.444173824159213,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 125,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-22T04:21:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.5231110068432,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.571165805690754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.245072352269222,
      "unilateral_faults": null,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-23T02:43:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.5035179780361,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.41381726074275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.281453340056,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.883837501980675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-23T08:02:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.799314323205,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.638698369369212,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-04T23:00:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.7745846890361,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.278757459984458,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-21T20:10:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.9628271566362,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.086249261383635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 83,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-22T04:12:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 83,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.908837049594,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.67026413949224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.804472558998102,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.735317704969,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.587564175213476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 22,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 11,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-23T01:51:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 22,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.6299005995513,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.50886244123093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 60.5072070285374,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 40,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-22T06:20:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.4147451259803,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.362656163193495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-22T04:21:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.7939198480567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.2012319421299,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-23T12:24:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.7350302187187,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.86522222010667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-22T06:20:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.2834532411562,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.523140403424865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-03T14:54:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.1892220782775,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.501934434108996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 277,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 102,
      "draws": 147,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-08-23T06:52:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1340.7970382156996,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.52045526776426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.2375081760512119,
      "unilateral_faults": 23,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-23T02:43:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1214.9205299918149,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-22T08:04:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 2001.572693385237,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 94.27284751416232,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T00:52:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1984.5756471110153,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 92.46710125142182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 99,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1963.1321087145507,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 90.96243393579934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.251875136730032,
      "unilateral_faults": 0,
      "wins": 181
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 274,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1928.0234348943654,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 88.3817448074802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 235
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-03T14:57:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1935.02209164043,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 87.48023052744581,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.294267162641567,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-05T01:40:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1921.1578815317785,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 86.85420097557086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1911.2358757943127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 86.25800515426019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.823251170389485,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1852.929717172452,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 81.15458170352487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-22T11:11:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1818.8752339259834,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 78.10288928195592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-05T01:40:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1811.7287474218497,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 77.21666620850746,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-22T10:31:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.3881365012405,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 76.16684999097536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-08-23T02:44:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1774.4665174138186,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 74.96104522556831,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 231
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.253047437652,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 69.3382874498687,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1702.4608950678553,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.9767252117913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-22T14:19:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1727.8905474681214,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 65.33787445900813,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1674.3839529154486,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 64.91216398908766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-04T21:09:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1664.3804338059472,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 64.57296544365413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-15T00:19:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1659.9607128670973,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.917443301992066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-04T22:34:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.7384364801353,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.893829202898324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-05T02:01:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1658.3798253586838,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.81899142309433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 179,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-08-20T13:06:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 179,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.7293692690507,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.50627032058176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-04T23:23:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.8634951956521,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 62.12239074156852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.7788762231971,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.677366694707196,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.409685569755814,
      "unilateral_faults": null,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-08-03T10:29:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.5922874284433,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.399729153600475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1624.9915664363414,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.302135745250496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-05T03:41:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.1656521686612,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.28160282112335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-08-05T03:41:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.8423835031147,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.64978060082346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-31T02:29:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1615.3072002247638,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.683472652436585,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemma-4-31b-it:8d94257f5348b920",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1605.3603699693099,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.53630433773744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-03T08:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.2220406835493,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.334280478082064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.103283115645,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.168257240229266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-23T07:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.0023160248443,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.37713182359818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-08-05T00:20:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.7468690047804,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.87934682152756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.259934288992827,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-08-05T03:49:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.5207424969149,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.367379627273316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-08-20T05:12:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.330410553067,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.18889318674271,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:42:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.6612634811117,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.98624033015518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-05T04:51:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.6242718976087,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.75082800967719,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-08-20T12:15:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.2966805223457,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.59420148801351,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-31T00:59:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.2082474431916,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.586976538895975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-15T02:19:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.611974494223,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.581984750264844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-05T02:08:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.4972105951804,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.42159236209911,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-20T12:14:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.3039721739203,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.7884886977324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-08-05T03:00:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.335337787397,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.69921153212445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-23T02:44:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.9118638803197,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.62541697170394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-03T14:14:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.6607990856423,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.20092432661375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-03T12:11:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.729054266692,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.0033758790599,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.9642531639468,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.951577978721,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 610,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 220,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 275,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 610,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.2233988941953,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.94753611433414,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 335
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-08-03T10:18:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.2909017340082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.89836516661261,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-03T14:57:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.312046490709,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.60093706896381,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 89,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-08-05T04:42:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.5178969518408,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.353895713407034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.137645938622816,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 11,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.8596132907571,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.94363834256713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.691509009023,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.77369810249913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.867968636721,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.28009274749246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 335,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 130,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 144,
      "max_score": null,
      "measured_at": "2026-08-22T23:45:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 335,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.0026260489992,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.197554884890174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-04T23:21:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.507550969813,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.175510141908525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-08-22T11:11:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.479690855548,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.525392048416236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:stepfun-step-3-7-flash:dfa24619f0407197",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-05T02:51:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.671430011153,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.477038427166434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-23T14:10:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.444849455973,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.24945473815348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 73,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.7914352128794,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.134814130021056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.570138866854082,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-05T02:08:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.9526866740612,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.38149773221454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 24.160953931632804,
      "unilateral_faults": null,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 157,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 157,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.7110311244185,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.519868263300424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-23T07:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.077411720965,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.140227782544386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 22,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 11,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-22T11:34:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 22,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.722998103657,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.02675226585254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 60.5072070285374,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-05T01:37:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.0462009965422,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.468260024253375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 93,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.579607297685,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.23068051946542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-08-03T11:29:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.7266136050657,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.68105445209972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-08-04T22:17:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.5690847750013,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.485310968950955,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-03T11:38:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.0736718738399,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.40888752062887,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-08-05T01:10:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.9826435606906,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.6367117182378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 91,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-08-05T00:09:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.9789820510734,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.15142583047198,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.686045325052198,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-20T12:56:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.4912588279985,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.65403638689062,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.807691416014,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.08609625332008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 121,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 185,
      "max_score": null,
      "measured_at": "2026-08-22T11:34:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.4869964909099,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.451721920222965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.8875852525139,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.17279269378332,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-08-03T12:50:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.2526700075625,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.763744651369436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-08-03T10:09:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.039006789118,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.840832148787285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-03T11:37:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.1338655756442,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.936055258537635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-07-31T03:33:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.5451243534771,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.95623962001668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.5924060058305,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.940983948757605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.7474591280127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.44275909587383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-08-22T14:19:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.3392576198007,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.10005925612763,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:mistralai-mistral-medium-3-5:6deb1b60bb205df7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-03T11:38:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1366.1081717055815,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.950977461561465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 77,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-07-31T03:33:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.368805685414,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.702868925973476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.867341638060083,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.1173082540881,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.19854110959529,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 365,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 133,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 243,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 365,
      "rating_method": "sequential_elo",
      "raw_elo": 1315.0698482131118,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.528261127510206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 135,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.182645360226,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.124865522470365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.2943419813913195,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-08-22T10:50:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.3355817153363,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.914142734486916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-20T12:25:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.410320453481,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.01400834375168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.4616251701777,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.506339570901225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-04T09:17:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.139212875865,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.279757091350554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 75,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-07-31T03:33:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.428283867453,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.079789578479307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.60765757439077,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1289.417656335887,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.078992764114222,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-08-22T10:50:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1285.0923577468707,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.820653512829104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-08-05T04:51:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.1782378757614,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.86430103882667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 296,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 218,
      "max_score": null,
      "measured_at": "2026-08-22T23:45:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1223.5192759386232,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.141806979414127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-20T12:05:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.8106711339308,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.725327714421983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:mistralai-mistral-medium-3-5:54288de170df8ebb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1215.6711985096656,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.36438641581923,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-08-04T21:09:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1207.2298320637442,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.847704758895738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 83,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 128,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1177.5020483483413,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.10631739223014,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.807372224754609,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-08-05T00:53:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1174.3948018938386,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.711146730771695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 242,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1156.0898611341393,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.247158692047016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1154.0769237728996,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.808040655611663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-08-05T02:32:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1147.5879156708982,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.568992620174647,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1146.4306765922527,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.508036486618778,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 253,
      "max_score": null,
      "measured_at": "2026-08-22T12:02:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1129.252871556389,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.90861104944561,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 85,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-08-03T22:34:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1134.3619315082324,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.33176752068492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.19101199758159,
      "unilateral_faults": 4,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 181,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 148,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 181,
      "rating_method": "sequential_elo",
      "raw_elo": 1100.5438465639747,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 15.533730958964114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 324,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 118,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 277,
      "max_score": null,
      "measured_at": "2026-08-22T19:33:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1046.1571521330118,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 10.571254109747576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-08-04T23:59:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 935.9987215696694,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-21T05:32:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 2004.117017853337,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 93.18006300131891,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1975.6465528059348,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 91.56194509481253,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 248
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 113,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1964.5138371126773,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 90.59930630959718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 257
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-20T17:51:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1956.1813224870132,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 89.25646806706095,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1957.933835666878,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 89.17064281296983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-05T00:01:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1929.4026084325167,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 86.36800772140613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-22T11:41:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1895.3746720098352,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 84.06596764154368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-22T20:09:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 89,
      "rating_method": "sequential_elo",
      "raw_elo": 1884.4844196491322,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 83.09168848413222,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.954627669472988,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-03T12:16:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1886.2628217788806,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 82.8497697558789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-03T14:42:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1884.0000254094712,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 82.54672029424074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-03T12:25:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1864.5341381574124,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 80.84833683146083,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-03T08:42:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1852.9315796761991,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 80.14817108632784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-03T10:32:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1849.5527583256137,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 79.45887582150341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-03T10:57:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1820.3562853548483,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 77.40648648738761,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-20T18:11:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1788.6250256792016,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 75.15416974608023,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-08-05T00:01:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1782.5107591539809,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 74.17041747029772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-03T07:40:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1761.3115017129503,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.53293912084276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-03T05:25:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1715.7619684800297,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.98589007065465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-03T13:30:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1705.0975680441916,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.70578978678658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-03T11:32:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1701.327703247478,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.33768307109139,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-03T11:04:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1692.7406046026997,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 66.56206174162008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-20T21:54:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1673.0845945046149,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 66.35935969494538,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-30T23:51:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1695.5081693751965,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 66.27613202821979,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 93,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-22T11:41:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.5047561892463,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 64.73769106673069,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1646.3542719474497,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.14422335372282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-08-20T21:14:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.7663053252722,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.0083250910945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 108,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.5056153716068,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 62.48746584354412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 176
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-08-05T03:41:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.8708605783158,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.89486875016836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-22T22:29:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 91,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.7147784478864,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.35124581231818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.378603514268699,
      "unilateral_faults": 1,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-20T18:12:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.4547207601838,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.91814020044125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1615.8418485040806,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.61195345345551,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-22T13:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.375142289731,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.52933478522943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.9544501736414,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.12787105389861,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.7137751991481,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.57776973557898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.466769200052298,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.3099870611559,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.56864288533566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.8399247445086,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.591838652401584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-05T01:59:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.5886286061254,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.20947020939446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-05T01:53:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.603307582626,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.42832822067658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-08-03T13:58:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.6488159742216,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.74330710655394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.1910999620195,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.128166821353254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-22T19:42:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.153408293399,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.386274611099374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.7715708378887,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.331168423892514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.0933915077662,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.01249738616022,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": null,
      "wins": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.0020375469994,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.100496566401134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.026656325279454,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T04:57:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.379331282502,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.05565583214185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 159,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-08-22T18:02:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 159,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.5552783412897,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.928109855002525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-08-20T21:54:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.3777590913119,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.921447482930446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-08-20T18:11:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.5889769331868,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.8069765902766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 74,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-07-31T20:23:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.2024013371195,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.09231852753391,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.000430913942129,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-23T12:25:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.0114222032025,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.06957808560736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 583,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 201,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 280,
      "max_score": null,
      "measured_at": "2026-08-23T04:58:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 583,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.398635934153,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.19784527381407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 286
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.4830994560295,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.03537257988135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-03T09:49:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.81989412051,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.66745425520703,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 97,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 97,
      "max_score": null,
      "measured_at": "2026-08-05T04:32:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.509690149318,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.921378822609434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.47889689397148,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.8627003840757,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.5973483966481,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-22T16:31:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.5925491348792,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.93379015513136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-05T04:57:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.828057804587,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.816521510440936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 288,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 147,
      "max_score": null,
      "measured_at": "2026-08-23T00:33:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.4894914486981,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.980742920105875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-05T00:01:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.1280740563188,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.55383945263552,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-08-03T12:10:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.244562486499,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.30821047229321,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.1728462442638,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.62272982536658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-08-03T10:58:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.619465594597,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.60739618718008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.8317645204697,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.56381339180203,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-08-03T09:47:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.7039967938965,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.498198272140634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-08-04T23:08:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.3428545385407,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.617353114418286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 81,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-04T23:17:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 81,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.606033323522,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.29134777487506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.465763037423269,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.1904394516557,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.83680633654252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-31T02:02:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.718765099697,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.31086220995625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-08-05T01:46:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.1489778493396,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.547794543772895,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-08-05T04:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.647741311623,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.30072691137755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 111,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-08-04T20:06:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 111,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.3710022776015,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.6741764977918,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.4955591261534025,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-03T12:29:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.5359335828546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.20986690104408,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.605991764229,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.54244701098439,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-23T12:15:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.7352199144916,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.40170202397549,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:mistralai-mistral-medium-3-5:6deb1b60bb205df7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-05T00:42:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.437842566501,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.28354233376265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemma-4-31b-it:8d94257f5348b920",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-03T13:20:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.2633420492373,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.24500604167221,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.1475676513953,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.1510974048913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-05T00:42:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.778953761991,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.00479516375429,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-08-23T00:03:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.769380358261,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.8828822319936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-23T04:48:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.0794653970897,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.659461887948076,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 21,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-23T00:33:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 21,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.625457434903,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.298263426455435,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 62.850358177805205,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.2789954568457,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.30669861449365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 129,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 223,
      "max_score": null,
      "measured_at": "2026-08-22T19:42:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1280.086612399988,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.20187949344528,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:stepfun-step-3-7-flash:dfa24619f0407197",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1286.5573647608894,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.9662488064309,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 83,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 83,
      "rating_method": "sequential_elo",
      "raw_elo": 1285.0945886378513,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.519767162748906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.804472558998102,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 325,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 212,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 325,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.9834845152213,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.035368345546885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-05T02:42:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1289.8281165492485,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.775234501033314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 27.779077868707382,
      "unilateral_faults": null,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-05T00:53:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.7125698415605,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.46308983512399,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-22T23:34:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.7844100164866,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.28416015452614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:mistralai-mistral-medium-3-5:54288de170df8ebb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1269.3787546862945,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.129646707507366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-08-20T21:45:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1260.4296004941673,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.66305165235034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 93,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-08-05T03:19:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.1713265502815,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.370496584013946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-07-31T00:54:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1261.0646377191872,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.283145533114592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 74,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1260.2930330590852,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.21820378332707,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 135,
      "max_score": null,
      "measured_at": "2026-08-22T10:20:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.6020053075358,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.146595980997496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.132002100700243,
      "unilateral_faults": null,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-05T00:52:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.9871534436184,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.12382384874148,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1238.9945909503178,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.822041323047518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1233.8513345112337,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.594696782513516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1212.912535347638,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.46626922181831,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1208.098508332924,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.29442357821482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-08-22T23:34:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1202.0009439276766,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.70848810998782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 165,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 118,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 165,
      "rating_method": "sequential_elo",
      "raw_elo": 1191.2017859373725,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.677590362951314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-08-21T05:34:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1169.8992765543176,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.952752097603227,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 115,
      "max_score": null,
      "measured_at": "2026-08-20T21:45:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1163.5476894293736,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.342189962527502,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 118,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 256,
      "max_score": null,
      "measured_at": "2026-08-23T00:03:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1157.4214480942765,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.76063329257293,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-08-05T03:19:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1139.6621346195743,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.257450141021867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 94,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 184,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1095.9852006337294,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.22866796894646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.5190135939585359,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-05T04:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 2007.7650814322424,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1985.9471428986744,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 98.38140095757626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1943.974131521536,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 93.82012264656494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-19T21:21:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1908.5825702078523,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 90.48850476973648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 79,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1883.547354485846,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 87.44155540902236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.419488455005332,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-19T21:56:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1852.419205680889,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 84.56963011340204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-03T14:13:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1824.0062989974588,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 81.36870015249958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-05T02:27:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1805.412687918018,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 79.13676897206143,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T03:23:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.5232339769955,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 77.77956211899175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-05T01:18:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.5903445158342,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 76.39149789263541,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-22T14:34:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1764.6335863223985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 76.29165283136004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1759.9984530561082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 74.93025959728134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-05T03:27:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1752.1617029482936,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 73.85605709393225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-08-22T15:50:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1732.781357799889,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 73.02102977984342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 196
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-05T02:43:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1741.7863118703656,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.77919861333487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-04T20:07:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1737.270344317228,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.31048780319064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-22T23:00:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.1032480369697,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.2896551782984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T04:28:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1736.9661240517378,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.16061484597145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.0113447747601,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 70.51569207279049,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-03T08:56:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1704.7019054474856,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.87219421844685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-05T01:31:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1702.8026322218134,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.84294122769712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1745.028439951044,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.66906686669674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-08-23T02:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.7238466980018,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 65.68620340611055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-08-05T02:27:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.3057314183425,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 64.8042465369897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-04T22:51:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.8923428169323,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 64.32521389783669,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-08-03T10:15:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.6540509725637,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.528190114310334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-05T04:28:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.6647109838646,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 62.86088508787239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.3758195563273,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 62.569827155594346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-04T21:03:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.281190088032,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.26423443502467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:moonshotai-kimi-k3:ccf8a3c1c9260d55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-19T21:33:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.0632436917545,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.356605978893036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-07-31T03:01:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.1122667994803,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.64226842671745,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.928761438070325,
      "unilateral_faults": null,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-03T15:11:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.3281773288047,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.19331770120144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.771978631998,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.923104326447486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 96,
      "max_score": null,
      "measured_at": "2026-08-19T21:21:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.6069463139568,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.278112032107714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-07-30T20:24:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.6688272885392,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.90520340006413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 119,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-08-22T19:47:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.0074698000692,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.64840056444847,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 1.042462425705284,
      "unilateral_faults": 0,
      "wins": 155
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-05T01:45:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.9166268461142,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.619553407262025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 309,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 144,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 305,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.4751430308143,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.01429727686298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.8790445826737,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.99459166857962,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.8690234891826,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.65187154398772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 93,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-22T19:47:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.3599516347117,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.034378723576836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:36d8ebdcb946256c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.490807576366,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.982816468950794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-31T01:11:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.6193285283734,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.449200646157834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-08-04T01:46:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.060781937911,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.39005509336917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.957067918206963,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-22T23:00:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.6587539842521,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.37264260162897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.9395388467756,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.209975643465064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 19.267903630526114,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.1576126409782,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.02977084911192,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-08-19T21:21:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.6448959972681,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.63125807718102,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.4758066512193,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.52329772108889,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.1505201787807,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.25998902213876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-23T02:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.254789411236,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.16395464120409,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-22T19:11:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.2174214587583,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.9850812289486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-05T00:37:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.7368378046194,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.573486962202864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.9397208469782,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.24161735863407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-05T03:34:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.3408603140847,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.83708028920805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-22T15:50:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.2649898641687,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.504378523447755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.9631011121937,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.03435356364199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 608,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 221,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 326,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 608,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.5992503742432,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.0302536987219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 282
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-05T01:37:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.6293568171732,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.901696725852915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 303,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 154,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 303,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.0791092283798,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.86769680909644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-08-05T02:09:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.6954722538387,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.38961044453501,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.6571114899198,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.145052128337795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-03T15:18:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.504688670992,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.06936748228342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:inclusionai-ling-3-0-flash:20c76d20ae9b2569",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 206,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.2579842748223,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.039137688291845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.992023749735065,
      "unilateral_faults": null,
      "wins": 160
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-03T12:28:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.05224599759,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.8080936476681,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-08-05T01:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.4354314549128,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.715724086496124,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 190,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.7430806795305,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.07920799575945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.283112930469331,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.5715457857082,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.8825963105233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 20.686604258614558,
      "unilateral_faults": null,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemma-4-31b-it:8d94257f5348b920",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-04T21:46:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.8604269782086,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.44657904798219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-03T12:43:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.3690275885945,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.395576864441175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-23T12:27:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.0816236736982,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.64180228110675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 96,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.3017135371133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.923736548942394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.19101199758159,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.9786554793234,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.80079783582027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-19T21:31:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.0330257928692,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.35125414343914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-08-23T10:07:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.9568971055057,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.0307879145991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-22T06:50:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.0796217693523,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.00669500599334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-07-31T03:07:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.295129846862,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.67741814723562,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.4711027318722,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.06804835684683,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.4789526855327,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.04689513213039,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 187,
      "max_score": null,
      "measured_at": "2026-08-23T10:07:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.2444957042999,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.23200509894748,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-08-05T04:09:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.3193424919139,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.262658898597685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.6943937413528,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.18021347469483,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 11,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.4252730885935,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.525553812172575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-03T00:20:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1357.2220634238477,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.80737392306428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 89,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-05T03:50:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 89,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.721001533367,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.63495353216882,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.954627669472988,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.4372322496993,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.543087970431298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1337.8847198438093,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.166262426165083,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.1870209205915,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.15058763153171,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-05T04:09:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.8860586083808,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.09131527235869,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-08-03T11:10:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.4878955652127,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.717577482950762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 107,
      "max_score": null,
      "measured_at": "2026-08-19T21:43:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1306.4568832534878,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.874737705095153,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 118,
      "max_score": null,
      "measured_at": "2026-08-19T21:34:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1295.2414425828902,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.888932528351898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-08-05T04:12:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.3603544346433,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.27162069011934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-08-22T06:50:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.4800377038869,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.78170138825857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 82,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1278.282398636208,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.88114022139318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.29009959559265,
      "unilateral_faults": 4,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-08-05T01:38:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1264.6371016053838,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.563915845571497,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-19T21:57:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1305.0776107344343,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.997140822640443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:mistralai-mistral-medium-3-5:54288de170df8ebb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-05T04:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.208763210193,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.89636625730998,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-03T21:49:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1224.0896973580377,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.047634614739106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 2,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 113,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1169.155353986958,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 14.602532202469558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-08-04T23:43:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1160.2853336204507,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 12.425400361217248,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1151.7537351331357,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 11.847787789192054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-03T22:56:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1154.4683223010247,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 11.821654639826498,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 2,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1144.6688037728486,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 10.490412921476183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 138,
      "max_score": null,
      "measured_at": "2026-08-22T14:34:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1114.7430613418464,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 9.05968322587179,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-08-04T01:46:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1108.5181051201985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 7.108412173273799,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 2,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 135,
      "max_score": null,
      "measured_at": "2026-08-22T12:49:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1092.4543600337247,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 6.641760874582254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:qwen-qwen3-7-plus:cdc5232f1e60910a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-08-04T01:12:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1075.8218147652353,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 3.600933227553536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 2,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1045.4789996487496,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 0.5096881306947669,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:mixed:google-gemini-3-1-flash-lite:f12274812b7e4c60",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1044.278117743902,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-fable-5:9765333017ba86fe",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-05T04:44:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 2039.7954541913955,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:moonshotai-kimi-k3:f0bfe8c58b2cc988",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 2018.027571089958,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 98.88106339111127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-5:5e133fd8ec34ed0c",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-22T17:44:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1945.9379565959005,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 91.324739517719,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-5:a7aa1873ad17dbcc",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-04T23:52:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1917.0549563802338,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 87.21199208118166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-4-5:365663c1de2ba20d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-22T18:02:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1890.764208012442,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 85.5368320379681,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 142
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:e2ff6744eb1bb7c6",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-21T15:41:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1878.7242423201383,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 84.27791783076424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 140
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-5:b56db7c91f30e821",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 91,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1888.389709769168,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 84.14512161801667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.380913286308589,
      "unilateral_faults": 0,
      "wins": 156
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:ec6362fd3d2a0220",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1883.2982680044097,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 83.58905380078096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:e615ab726629f0c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1857.759542012682,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 80.96609226971566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:e7389fafab42de55",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-22T23:22:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1801.5518334727867,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 75.08894239706439,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-fable-5:99e7b840e9269907",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1794.8063548988707,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 74.18412112706072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-8:c5e685ce6c400bea",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-03T04:47:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1792.8722395599843,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 73.81276758326433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-5:a77a9da79f1450e0",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T03:02:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1788.7771703951637,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 73.75320729186035,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-5:a953aed661ace78d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-05T04:44:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1777.792006324548,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.26518773471317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.154975300928378,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:13a24e3021af753a",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1755.9191643788624,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 71.15699062079223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-8:95b343605f7f7184",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-05T02:16:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1756.3114534666295,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 70.21149192288846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:959db58a0f4d59b9",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-03T01:17:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.3352174883826,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 70.0969711174775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:a1a9848a1d14b67e",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T03:33:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1741.2522481037183,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.95924601863939,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-5:2bf46853c4c2a3bc",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 110,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-08-21T15:53:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1724.7767888250444,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.65894839210796,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.0009297552497305,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-spark-1-2:0ef600658249027b",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-21T18:11:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1696.938698515543,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 64.10305893387694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:moonshotai-kimi-k2-7-code:0eac35852db14de0",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-03T11:19:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1688.6711614594897,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.086489595554106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:1f51e395856c1899",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": null,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "legacy_shared_thinking_budget",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "budget",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-07-31T20:23:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1666.6691549579436,
      "reasoning_bracket": null,
      "reasoning_level": "Historical thinking-budget setting",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "mixed",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "budget",
          "requested_effort": "historical-thinking-budget-setting",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Historical thinking-budget setting",
        "reasoning_bracket": "mixed",
        "reasoning_bucket": "historical-thinking-budget-setting",
        "reasoning_bucket_label": "Historical thinking-budget setting",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "budget",
        "requested_reasoning_effort": "historical-thinking-budget-setting"
      },
      "reasoning_setting": "historical-thinking-budget-setting",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.12735715152601,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.355683254666296,
      "unilateral_faults": null,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meta-muse-spark-1-2:539f99e7c4c4b6ea",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-21T18:12:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.41020376169,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.44710258784996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-sol:92a27bf667504f91",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.2299897743615,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.42825918291155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:483e8409583d40a0",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-15T02:22:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1649.4348299353023,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.03633551296827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-5:1a25631bf54a6363",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-02T22:46:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.390503669571,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.44347013105038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max:644816d2bc8a5f5c",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-22T18:02:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.7448564416845,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.180067856085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-terra:75cc7f062ffaf091",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-04T22:26:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.3366324646952,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.49765579998893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-nano:4caf0453cfb54e62",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 81,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-08-04T20:41:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.610446657007,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.13298974653004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.807372224754609,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:b4583ef7c04d45cd",
      "capped_draws": 97,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 97,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-08-22T23:22:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.6648885423429,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.92804253858354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:5ea14bc9644b6a2b",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-31T20:23:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.7519312912373,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.193398652066804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 18.466769200052298,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 454,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:1084c60ee563e860",
      "capped_draws": 187,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 176,
      "draws": 187,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 137,
      "max_score": null,
      "measured_at": "2026-08-22T14:19:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 454,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.7257361361333,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.3120429850668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro:a4cf9c7798e0d7dc",
      "capped_draws": 73,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-03T03:56:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.051856910287,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.222502598035426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stealth-ox-alpha:fe3b437dca2c4367",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.5181600374551,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.46972348405135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:minimax-minimax-m3:6639861dd7b73e51",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-02T23:32:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.4645617409897,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.03473455786694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:3449c1aec50b70b2",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-04T21:46:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.177337369126,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-2",
        "reasoning_bucket_label": "Reasoning enabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.11119431698934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-nano:8753e840d1cee063",
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 85,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.1120170443423,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.07682565953572,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 10.243458840961587,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:a86621e2793b5dec",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-15T01:49:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.1322671330724,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.54296563169207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 103,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:672219b99ff5a80c",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 103,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.0480758610206,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.49874489923657,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.279033784546012,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max:a791831295f0ee80",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-21T20:35:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.547974554364,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.46830457086832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy3-preview:173ea133649c5bcd",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-03T12:45:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.1794699081136,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.11348750799539,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:f70fd8105d3dfec2",
      "capped_draws": 57,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-03T12:36:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.633977758998,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.99479029724878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-terra:08cc40e91e1568bf",
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 48,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-05T03:28:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.1846041302629,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.74024783687207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-1-flash-lite:4c9cdde1729642af",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.4974729461187,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.003099708266724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stealth-ox-alpha:6719f8157bcde29f",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-23T14:11:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.424913229797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.82700014011026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-mini:e296afd987da0af3",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.4598339312142,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.437872589956235,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-max:fa240f0afd3eda59",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.2167537575,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.278925993132454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-5:53d4c02c8a9496db",
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 76,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T01:22:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.3708835943642,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.263590475601305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:f9a4cf175428ff96",
      "capped_draws": 79,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:33:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.316763828664,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.18482189543753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:tencent-hy3-preview:7ef07d2849ca4d92",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:32:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.9981872068206,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.009683345730224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5:16f7def69ce10ccd",
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-04T23:45:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.1578264572643,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.948611997746326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:be72f75fe8d3007b",
      "capped_draws": 68,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-31T02:32:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.840451333209,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.7686972873823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemma-4-31b-it:e2b2f6f0f78a1f3f",
      "capped_draws": 82,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-04T22:07:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.8830391614035,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.474836925823645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-plus:e4e482b5c34e690f",
      "capped_draws": 88,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 88,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T00:36:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.7461884339903,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.251405081567306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:minimax-minimax-m3:6f48906184a5bdb8",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-05T01:31:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.7357176254268,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.21198399845459,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:a3e60c7aa64704be",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.7124167603577,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.04456627680913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:865c6d4e9c2ee4b8",
      "capped_draws": 80,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.8224215244215,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.0364485323938,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling-small:c4a079d6b58a2c73",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-22T23:00:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.5508035025312,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.74879684007773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:x-ai-grok-build-0-1:55f4f20890a40d69",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-04T23:07:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.9235515651562,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.62877770432017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:z-ai-glm-5-2:f14efcbac580ffaa",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.9737693629816,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.627097160286695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nex-agi-nex-n2-pro:b04b6e7c11ec4633",
      "capped_draws": 87,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 87,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.5476658850525,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.23396365548673,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-8:8ccf8977401d94db",
      "capped_draws": 75,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-04T23:29:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.511822163267,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.12565451149703,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-4-1:731bd482a4919a05",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.8185070181821,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.05316059344751,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:d658f92b65107751",
      "capped_draws": 61,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T02:53:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.8830365675533,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.88171545537361,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:cohere-north-mini-code:4a23759df70ab26b",
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:33:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.7240598409555,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.85875457644092,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nvidia-nemotron-3-ultra-550b-a55b:94c7956182cf2d89",
      "capped_draws": 120,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 83,
      "draws": 120,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.5749166804935,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.843689445221074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.951570146038407,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:1ebaee0e9d08b232",
      "capped_draws": 69,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.790186771671,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.8121598719359,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4-mini:9285646640165917",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-04T06:58:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.788041459873,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.54787145753626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 2,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-flash:dac448fbfe2a5737",
      "capped_draws": 128,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "draws": 128,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-31T03:35:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.5458902114271,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.54211074905695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-8-max:7b21229bd01e0b5e",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.3660051372515,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.42398580815915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling-small:6603774c29b8a046",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-21T20:21:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.0959389047707,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.26674941355504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:024b37c390436d5a",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.564866061363,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.05738226960813,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:deepseek-deepseek-v4-pro:d03a9ec0db9a8b52",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-04T09:10:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.9553709497593,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.98184099437737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:235a446f3a9f9cd3",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1395.9633455247022,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-1",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.369923371940445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:moonshotai-kimi-k3:6a00f2f5a49a8584",
      "capped_draws": 129,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 129,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.978890026653,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.270736967846446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meituan-longcat-2-0:45102822fc5f9296",
      "capped_draws": 181,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 181,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:49:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.5031523076473,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.25995087039648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-1-flash-lite:78a7cfd3a790e8a8",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T02:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.2575126535978,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.18804360592281,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-terra:0983009cb1ffeee4",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-04T07:10:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.9303824976794,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.16201019317678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 2,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 14,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling-small:f1451a0a6af20650",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 6,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-21T20:35:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 14,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.7060664706091,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.15114034501958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:poolside-laguna-s-2-1:533b6103a5973424",
      "capped_draws": 179,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 101,
      "draws": 179,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.5631121202853,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.11405727592425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.364069356670375,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stepfun-step-3-7-flash:0e0f63cf65826515",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T00:38:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.660028685881,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.024524339620434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5-pro:4b9c2bdb10b14302",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-04T08:41:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.997724777921,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.43712263783562,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-sonnet-5:73f1b29a5c45562d",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-21T15:02:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.1626713883547,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.349808387715242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 288,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:inclusionai-ling-3-0-flash:1ed2a890413ad375",
      "capped_draws": 244,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 107,
      "draws": 244,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash:free",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.3105536667902,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.255249763757412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:qwen-qwen3-7-max:a92ef5f3c3f212e3",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.4580243708433,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.087752265854334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 305,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:meituan-longcat-2-0:bed5035a5082adf8",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 117,
      "draws": 95,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 150,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 305,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.878037318353,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.011204993640277,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-6-flash:b574aaabaed70f28",
      "capped_draws": 226,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 123,
      "draws": 226,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 92,
      "max_score": null,
      "measured_at": "2026-08-23T00:15:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.1951020946215,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.468489170149333,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:mistralai-mistral-medium-3-5:6deb1b60bb205df7",
      "capped_draws": 87,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 87,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T04:49:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.2539193575665,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.076430145642476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 95,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-4:cea8a68bd875deb9",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 95,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.526850657215,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.98416128073413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 7.281036307982882,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 332,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:poolside-laguna-s-2-1:07eac22bdea1b9b3",
      "capped_draws": 224,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 126,
      "draws": 224,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-08-22T11:41:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.6049159769764,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.56068444949395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 331,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:55634764b9427e4e",
      "capped_draws": 225,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 121,
      "draws": 225,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 92,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 331,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.3683142272248,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.008271779974574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5:3bb27dbc092c7ff2",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.3112742107332,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.79276252693172,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash:5712a3e29dc27925",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-03T02:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.7075347534644,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.62507347872291,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 157,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:o3:29970c6bc7db3c37",
      "capped_draws": 105,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 105,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 157,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.5104644614696,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.51885536161832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:claude-opus-4-5:9f0371e603fb81bd",
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-21T15:41:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.9635954463263,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.34925891692476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:281eafa14f6ff011",
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1339.095194087079,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.872484354770776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:cohere-north-mini-code:959513c67c4e5ee3",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code:free",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-05T04:28:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.9716806578233,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.8658776184786,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 33.16054548991772,
      "unilateral_faults": null,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:0bab1c3ea19c7cb7",
      "capped_draws": 209,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 209,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.1974425120047,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.219997210607445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash-lite:5943a501fa6113ab",
      "capped_draws": 100,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 100,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-21T18:21:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.9225797807596,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.835835838194487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 153,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:thinkingmachines-inkling:b27963da4b6944f2",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 92,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-21T18:11:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 153,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.0261862668438,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.64774117358596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stealth-ox-alpha:dfb3dd7361cfa1a2",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.0853900991224,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.439932585091782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:29e28a5adce9180a",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.6533845849854,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.07186922308482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:e05ef4cc93414f96",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-21T18:10:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.0394459572435,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.22675683362329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:google-gemini-3-5-flash:2637a22cd82f12e9",
      "capped_draws": 57,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-05T03:58:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.0263767118158,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-intensive",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "historical-provider-setting-intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-intensive"
      },
      "reasoning_setting": "historical-provider-setting-intensive",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.174721344647317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:35035a0b78826dbc",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.6483928907644,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled (historical request variant 2)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-baseline-variant-2",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline-variant-2",
        "reasoning_bucket_label": "Reasoning disabled (historical request variant 2)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-baseline-variant-2"
      },
      "reasoning_setting": "historical-provider-setting-baseline-variant-2",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.71695375858572,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:stepfun-step-3-7-flash:b2de164dfb65fa47",
      "capped_draws": 99,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 99,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.5376746549155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.799140452263753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:openai-gpt-oss-120b:7785ef5b91a441ff",
      "capped_draws": 89,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 89,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-08-23T02:22:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.6137277486175,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.506744531570664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:xiaomi-mimo-v2-5:32918e3c3e0fca83",
      "capped_draws": 40,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 40,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-07-31T03:36:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.8709169097879,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium (historical request variant 1)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-balanced-variant-1",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium (historical request variant 1)",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced-variant-1",
        "reasoning_bucket_label": "Medium (historical request variant 1)",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-balanced-variant-1"
      },
      "reasoning_setting": "historical-provider-setting-balanced-variant-1",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.078359431984563,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:nex-agi-nex-n2-pro:a8c61d4550659ad0",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "unknown_legacy",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-08-05T02:33:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1217.152242285979,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "historical-provider-setting-balanced",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "historical-provider-setting-balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "historical-provider-setting-balanced"
      },
      "reasoning_setting": "historical-provider-setting-balanced",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 13.67320578769338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:mixed:gpt-5-6-luna:15a0f0a09f9eb8e5",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "full_freedom",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-08-22T11:52:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1083.8717985479768,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "historical-provider-setting-baseline",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/mixed"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "historical-provider-setting-baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "historical-provider-setting-baseline"
      },
      "reasoning_setting": "historical-provider-setting-baseline",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/mixed",
      "track_name": "Reasoning Variants",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-fable-5:7f49308e40ed3ed5",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 16,
        "cost_basis_counts": {
          "local_list_price_estimate": 19
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 1.91725,
        "mean": 1.043635625,
        "median": 0.8756600000000001,
        "min": 0.33027,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 19
        },
        "run_count": 16,
        "token_priced_attempt_count": 19,
        "total": 16.69817
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 129,
      "eligibility_flag": false,
      "entry_count": 15,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 12,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "infra_failures_excluded": 4,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:44:21Z",
      "losses": 208,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 56.05592222052655,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1128,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 74.68960256062708,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 791
    },
    {
      "admitted_plugins": 41,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-5:e3a8c6d4d5f3bdeb",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 41,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 48
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 7,
        "max": 2.09943,
        "mean": 0.703821875,
        "median": 0.48028875,
        "min": 0.2178175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 48
        },
        "run_count": 48,
        "token_priced_attempt_count": 48,
        "total": 33.783449999999995
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 45,
      "draws": 473,
      "eligibility_flag": true,
      "entry_count": 41,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 41,
      "first_pass_rate": 0.8541666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-15T00:11:21Z",
      "losses": 542,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 51.301004509305145,
      "model_code_failure_rate": 0.14583333333333334,
      "model_code_failures": 7,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3195,
      "rating_method": "sequential_elo",
      "raw_elo": 1767.0059083658161,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 72.63357209239122,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2180
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-6-sol:355993239c1ccc35",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 1.17244375,
        "mean": 0.3844993229166666,
        "median": 0.23243875,
        "min": 0.10071375,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 25
        },
        "run_count": 24,
        "token_priced_attempt_count": 25,
        "total": 9.22798375
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 290,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 23,
      "first_pass_rate": 0.9583333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T05:21:14Z",
      "losses": 391,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 27.127464596852075,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2074,
      "rating_method": "sequential_elo",
      "raw_elo": 1711.2468735492096,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 69.85630076191232,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1393
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-4:b646b36fcd253b5f",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 27
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 2.2530275,
        "mean": 0.6328307291666667,
        "median": 0.26543625,
        "min": 0.0656625,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 27
        },
        "run_count": 24,
        "token_priced_attempt_count": 27,
        "total": 15.187937499999999
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 511,
      "eligibility_flag": true,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:23:52Z",
      "losses": 484,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 17.905822221963863,
      "model_code_failure_rate": 0.041666666666666664,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2089,
      "rating_method": "sequential_elo",
      "raw_elo": 1654.2667294627104,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 2,
      "repaired_rate": 0.08333333333333333,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 57.04876585166363,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1094
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:x-ai-grok-4-5:d65de196562f343c",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "evidence_basis": "Provider-reported",
        "max": 0.13495079999999998,
        "mean": 0.07082726666666667,
        "median": 0.0661398,
        "min": 0.0424244,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 34
        },
        "recorded_attempt_count": 34,
        "run_count": 24,
        "total": 1.6998543999999998
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 47,
      "draws": 786,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 20,
      "first_pass_rate": 0.8333333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T13:45:16Z",
      "losses": 907,
      "max_score": 91.324739517719,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 3189,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.1954422906456,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 55.237675475363496,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1496
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-4-8:66e9f46ea7415508",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 25
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 1.38945,
        "mean": 0.43567666666666666,
        "median": 0.20305499999999999,
        "min": 0.131495,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 25
        },
        "run_count": 24,
        "token_priced_attempt_count": 25,
        "total": 10.456240000000001
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 484,
      "eligibility_flag": true,
      "entry_count": 22,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:49:27Z",
      "losses": 473,
      "max_score": 80.14817108632784,
      "measured_at": null,
      "min_score": 15.975113871358344,
      "model_code_failure_rate": 0.08333333333333333,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1796,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.5737362227703,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 53.87002875976319,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 839
    },
    {
      "admitted_plugins": 22,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-5:6c8c03d567738842",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 22,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 26
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 4.4173,
        "mean": 1.10693125,
        "median": 0.4176025,
        "min": 0.12078,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 26
        },
        "run_count": 24,
        "token_priced_attempt_count": 26,
        "total": 26.566349999999996
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 649,
      "eligibility_flag": true,
      "entry_count": 22,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06"
      ],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:23:57Z",
      "losses": 459,
      "max_score": 93.82012264656494,
      "measured_at": null,
      "min_score": 19.58339791797017,
      "model_code_failure_rate": 0.08333333333333333,
      "model_code_failures": 2,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1832,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.0658774622516,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 53.267066860444224,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 724
    },
    {
      "admitted_plugins": 42,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-6-flash:6aba70247d100ab2",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 42,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 126
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.531673125,
        "mean": 0.264606278125,
        "median": 0.24728879999999998,
        "min": 0.0411735,
        "recorded_attempt_count": 126,
        "run_count": 48,
        "total": 12.701101349999998
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 47,
      "draws": 1589,
      "eligibility_flag": true,
      "entry_count": 42,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 34,
      "first_pass_rate": 0.7083333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T13:45:16Z",
      "losses": 1780,
      "max_score": 91.56194509481253,
      "measured_at": null,
      "min_score": 16.174375669656794,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 6,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 5984,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.3157387821625,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 52.27760470741041,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 2615
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-5-flash:c324fc4c43d7c8e1",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 20,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 51
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.6921525,
        "mean": 0.30153312499999996,
        "median": 0.335163,
        "min": 0.025422,
        "recorded_attempt_count": 51,
        "run_count": 24,
        "total": 7.236795
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 328,
      "eligibility_flag": false,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:04:52Z",
      "losses": 324,
      "max_score": 84.5317048418163,
      "measured_at": null,
      "min_score": 24.174721344647317,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1102,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 14,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 51.3066160991627,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 450
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:moonshotai-kimi-k3:601623cc06431dd6",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 40
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.6279041999999999,
        "mean": 0.2975122,
        "median": 0.2990655,
        "min": 0.0550338,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 40
        },
        "recorded_attempt_count": 40,
        "run_count": 24,
        "total": 7.1402928
      },
      "codegen_evaluated_cells": 23,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 47,
      "draws": 991,
      "eligibility_flag": false,
      "entry_count": 21,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-05",
        "GB2-06"
      ],
      "first_pass_admitted": 15,
      "first_pass_rate": 0.6521739130434783,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T17:46:55Z",
      "losses": 919,
      "max_score": 98.88106339111127,
      "measured_at": null,
      "min_score": 20.275423642118344,
      "model_code_failure_rate": 0.08695652173913043,
      "model_code_failures": 2,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3229,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.0503265455409,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.2608695652173913,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 49.98578029870014,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1319
    },
    {
      "admitted_plugins": 17,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:meta-muse-spark-1-2:3667fca8056828bb",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 17,
        "cell_count": 18,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.143734,
        "mean": 0.04530390277777777,
        "median": 0.035486000000000004,
        "min": 0.01939525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 20
        },
        "recorded_attempt_count": 20,
        "run_count": 18,
        "total": 0.8154702500000001
      },
      "codegen_evaluated_cells": 18,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 317,
      "eligibility_flag": false,
      "entry_count": 17,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 16,
      "first_pass_rate": 0.8888888888888888,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T02:44:09Z",
      "losses": 525,
      "max_score": 79.71591004614217,
      "measured_at": null,
      "min_score": 16.944819699504418,
      "model_code_failure_rate": 0.05555555555555555,
      "model_code_failures": 1,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1463,
      "rating_method": "sequential_elo",
      "raw_elo": 1568.90055051634,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.05555555555555555,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 48.33415064687674,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 621
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-opus-4-5:7a31aface18eaea9",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 39,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 41
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.512955,
        "mean": 0.2537023958333333,
        "median": 0.20905875000000002,
        "min": 0.09594,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 16,
          "boardgame-list-prices-2026-08-08": 25
        },
        "run_count": 40,
        "token_priced_attempt_count": 41,
        "total": 11.203785
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 47,
      "draws": 912,
      "eligibility_flag": false,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 24,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-21T20:34:32Z",
      "losses": 1023,
      "max_score": 84.27791783076424,
      "measured_at": null,
      "min_score": 13.078411737521655,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3209,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.9295911454142,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 48.11001608960555,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1274
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-6-terra:97de4d20c6c50836",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 32
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 12.137519999999999,
        "mean": 2.8005991666666663,
        "median": 0.15809499999999999,
        "min": 0.0542775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 32
        },
        "run_count": 25,
        "token_priced_attempt_count": 32,
        "total": 67.27386999999997
      },
      "codegen_evaluated_cells": 25,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 661,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 17,
      "first_pass_rate": 0.68,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 24,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:18:32Z",
      "losses": 603,
      "max_score": 76.39149789263541,
      "measured_at": null,
      "min_score": 21.8994809309449,
      "model_code_failure_rate": 0.04,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1962,
      "rating_method": "sequential_elo",
      "raw_elo": 1536.3532324359662,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 7,
      "repaired_rate": 0.28,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 47.62657298276638,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 698
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:z-ai-glm-5-2:b52271e32d7b710c",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 26,
        "cell_count": 17,
        "cost_basis_counts": {
          "provider_reported": 47
        },
        "evidence_basis": "Provider-reported",
        "max": 0.14831665,
        "mean": 0.04690495967823529,
        "median": 0.030447832,
        "min": 0.0106770175,
        "recorded_attempt_count": 47,
        "run_count": 26,
        "total": 1.06760263506
      },
      "codegen_evaluated_cells": 26,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 45,
      "draws": 601,
      "eligibility_flag": false,
      "entry_count": 26,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 11,
      "first_pass_rate": 0.4230769230769231,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "untested_or_ineligible_settings",
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T14:35:20Z",
      "losses": 548,
      "max_score": 66.27613202821979,
      "measured_at": null,
      "min_score": 18.537461190466654,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1730,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.6025420140638,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 15,
      "repaired_rate": 0.5769230769230769,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 46.44888424274979,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 581
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:claude-sonnet-5:351ed472be23eda4",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_list_price_estimate": 24
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.50466,
        "mean": 0.15942958333333332,
        "median": 0.068377,
        "min": 0.049908,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 24
        },
        "run_count": 24,
        "token_priced_attempt_count": 24,
        "total": 3.82631
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 550,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 24,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:40:55Z",
      "losses": 736,
      "max_score": 83.58905380078096,
      "measured_at": null,
      "min_score": 18.648854275319852,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2034,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.0957818365973,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "anthropic",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 45.48859356108469,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 748
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5:509525aafb482b3d",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 31
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 3,
        "max": 0.45464499999999997,
        "mean": 0.18566328125000006,
        "median": 0.17276625,
        "min": 0.06945125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 12,
          "boardgame-list-prices-2026-08-08": 19
        },
        "run_count": 24,
        "token_priced_attempt_count": 31,
        "total": 4.45591875
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 349,
      "eligibility_flag": false,
      "entry_count": 15,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 12,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:19:06Z",
      "losses": 434,
      "max_score": 67.70578978678658,
      "measured_at": null,
      "min_score": 19.976294071045,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1200,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 44.52668228063902,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 417
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:deepseek-deepseek-v4-pro:d46bf919cbe90971",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.10909930499999998,
        "mean": 0.049205097625000006,
        "median": 0.034298199,
        "min": 0.005612805,
        "recorded_attempt_count": 28,
        "run_count": 16,
        "total": 0.7872815620000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 332,
      "eligibility_flag": false,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:41Z",
      "losses": 388,
      "max_score": 77.21666620850746,
      "measured_at": null,
      "min_score": 22.057846645260756,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 3,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1108,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 43.545245203742624,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 388
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:moonshotai-kimi-k2-7-code:3b6469f485258e46",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.226689264,
        "mean": 0.16037539425,
        "median": 0.140728509,
        "min": 0.10689655,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 1.283003154
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 37,
      "draws": 163,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-06"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:26:41Z",
      "losses": 193,
      "max_score": 63.086489595554106,
      "measured_at": null,
      "min_score": 23.435946683398193,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 572,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.42011970249428,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 216
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-7-max:2295a106326bfd7d",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.12185499999999999,
        "mean": 0.05695140625,
        "median": 0.036751875,
        "min": 0.015285,
        "recorded_attempt_count": 24,
        "run_count": 16,
        "total": 0.9112225
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 430,
      "eligibility_flag": false,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:35:11Z",
      "losses": 397,
      "max_score": 79.13676897206143,
      "measured_at": null,
      "min_score": 15.302941621960535,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1220,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.357283712111325,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 393
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-4-1:d5dcb828dbee1dd0",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.09459400000000001,
        "mean": 0.0571955,
        "median": 0.043012,
        "min": 0.032534,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 0.457564
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 228,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:31Z",
      "losses": 224,
      "max_score": 63.331047607164344,
      "measured_at": null,
      "min_score": 18.508036486618778,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 651,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 41.47586576190677,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 199
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:xiaomi-mimo-v2-5-pro:1f2ff8329154ac84",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 15,
        "cost_basis_counts": {
          "provider_reported": 27
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.2996388,
        "mean": 0.08564151856,
        "median": 0.0495450162,
        "min": 0.0057139812,
        "recorded_attempt_count": 27,
        "run_count": 15,
        "total": 1.2846227784
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 232,
      "eligibility_flag": false,
      "entry_count": 11,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.26666666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality",
        "generation_incomplete",
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:01Z",
      "losses": 369,
      "max_score": 68.98589007065465,
      "measured_at": null,
      "min_score": 25.444968645038077,
      "model_code_failure_rate": 0.2,
      "model_code_failures": 3,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 968,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 0.5333333333333333,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 41.0505200712072,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 367
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-4-1-nano:bf2b00ecdde1f74d",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 1,
        "cost_basis_counts": {
          "estimated": 1,
          "local_standard_estimate": 1
        },
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "max": 0.0023425,
        "mean": 0.0023425,
        "median": 0.0023425,
        "min": 0.0023425,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 1,
          "boardgame-list-prices-2026-08-08": 1
        },
        "recorded_attempt_count": 1,
        "run_count": 1,
        "token_priced_attempt_count": 1,
        "total": 0.0023425
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 25,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": 1,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 1,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality",
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-14T15:31:41Z",
      "losses": 67,
      "max_score": 39.72974279439747,
      "measured_at": null,
      "min_score": 39.72974279439747,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 39.72974279439747,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 60
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:x-ai-grok-build-0-1:657efc023ad7cc85",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "max": 0.07439860000000001,
        "mean": 0.060660574999999994,
        "median": 0.0565846,
        "min": 0.0485456,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.48528459999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 276,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:34:43Z",
      "losses": 241,
      "max_score": 67.9767252117913,
      "measured_at": null,
      "min_score": 21.895370370120215,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 726,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 39.4814143462601,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 209
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-8-max:3bcc7f6323eff7b9",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.40721066666666667,
        "mean": 0.19033848611111112,
        "median": 0.13741799999999998,
        "min": 0.066054,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 30
        },
        "recorded_attempt_count": 30,
        "run_count": 29,
        "total": 6.452750000000001
      },
      "codegen_evaluated_cells": 26,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 18,
      "draws": 132,
      "eligibility_flag": false,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 24,
      "first_pass_rate": 0.9230769230769231,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-08"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T01:51:58Z",
      "losses": 115,
      "max_score": 68.66906686669674,
      "measured_at": null,
      "min_score": 7.529917385447114,
      "model_code_failure_rate": 0.07692307692307693,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 409,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.6936171914656,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 39.06451930494661,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 162
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-4-mini:55f0d0ca5e9d66ef",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 17,
        "cost_basis_counts": {
          "estimated": 2,
          "local_standard_estimate": 22
        },
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "max": 1.503294825,
        "mean": 0.2156185632352941,
        "median": 0.169101,
        "min": 0.01245825,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-08-08": 22
        },
        "recorded_attempt_count": 2,
        "run_count": 18,
        "token_priced_attempt_count": 22,
        "total": 5.1688104
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 517,
      "eligibility_flag": false,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.8125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:55:18Z",
      "losses": 457,
      "max_score": 58.26867546532442,
      "measured_at": null,
      "min_score": 7.108412173273799,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1381,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 38.704261600934956,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 407
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-4-nano:21e1db315087268e",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 17,
        "cost_basis_counts": {
          "estimated": 2,
          "local_standard_estimate": 55
        },
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 8,
        "max": 0.26962149999999996,
        "mean": 0.03182758529411764,
        "median": 0.01676735,
        "min": 0.004854125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 2,
          "boardgame-list-prices-2026-08-08": 55
        },
        "recorded_attempt_count": 2,
        "run_count": 34,
        "token_priced_attempt_count": 55,
        "total": 1.0821378999999998
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 507,
      "eligibility_flag": false,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07"
      ],
      "first_pass_admitted": 10,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:55:07Z",
      "losses": 802,
      "max_score": 63.14422335372282,
      "measured_at": null,
      "min_score": 15.136633992883711,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 8,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2040,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 14,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 37.857809245731936,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 731
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:gpt-5-6-luna:0ccf02fcc67f023e",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0377622,
        "mean": 0.01391661875,
        "median": 0.00586915,
        "min": 0.0040101,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 25
        },
        "run_count": 24,
        "token_priced_attempt_count": 25,
        "total": 0.3339988499999999
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 604,
      "eligibility_flag": true,
      "entry_count": 24,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 23,
      "first_pass_rate": 0.9583333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:40:55Z",
      "losses": 857,
      "max_score": 83.09168848413222,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2058,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.4661702219637,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 1,
      "repaired_rate": 0.041666666666666664,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 37.80451197917878,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 597
    },
    {
      "admitted_plugins": 29,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:o3:54cad6d3f7756427",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 29,
        "cell_count": 24,
        "cost_basis_counts": {
          "estimated": 40,
          "local_standard_estimate": 29
        },
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 19,
        "max": 0.17217,
        "mean": 0.08358424999999998,
        "median": 0.0865375,
        "min": 0.037309999999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 13,
          "boardgame-list-prices-2026-08-08": 56
        },
        "recorded_attempt_count": 40,
        "run_count": 48,
        "token_priced_attempt_count": 29,
        "total": 4.201686
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 47,
      "draws": 597,
      "eligibility_flag": false,
      "entry_count": 29,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-08"
      ],
      "first_pass_admitted": 29,
      "first_pass_rate": 0.6041666666666666,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:51:52Z",
      "losses": 1760,
      "max_score": 62.569827155594346,
      "measured_at": null,
      "min_score": 2.8219078055756306,
      "model_code_failure_rate": 0.3958333333333333,
      "model_code_failures": 19,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 4006,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.7951736662321,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openai",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 37.46323340271141,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1649
    },
    {
      "admitted_plugins": 79,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:stealth-ox-alpha:2017c74462701082",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 79,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 112
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 112,
        "run_count": 88,
        "total": 0.0
      },
      "codegen_evaluated_cells": 85,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1,
      "draws": 224,
      "eligibility_flag": false,
      "entry_count": 66,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 62,
      "first_pass_rate": 0.7294117647058823,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "infra_failures_excluded": 5,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T14:12:18Z",
      "losses": 369,
      "max_score": 52.06957808560736,
      "measured_at": null,
      "min_score": 3.8514807674763087,
      "model_code_failure_rate": 0.07058823529411765,
      "model_code_failures": 6,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 962,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.8057114160026,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 17,
      "repaired_rate": 0.2,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 36.27021137287471,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 369
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:tencent-hy3-preview:f8fa673b07fb084d",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 25
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.007539277999999999,
        "mean": 0.0022565913437500003,
        "median": 0.0014932259999999998,
        "min": 0.00090937,
        "recorded_attempt_count": 25,
        "run_count": 17,
        "total": 0.041725612999999995
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 346,
      "eligibility_flag": false,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5294117647058824,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:51Z",
      "losses": 369,
      "max_score": 72.88756496655336,
      "measured_at": null,
      "min_score": 13.368124963630589,
      "model_code_failure_rate": 0.23529411764705882,
      "model_code_failures": 4,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1024,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.23529411764705882,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 36.068609227458595,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 309
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemma-4-31b-it:54dd73921471ddad",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 14,
        "cost_basis_counts": {
          "provider_reported": 23
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0092087,
        "mean": 0.004466478571428571,
        "median": 0.0042425399999999995,
        "min": 0.00144036,
        "recorded_attempt_count": 23,
        "run_count": 14,
        "total": 0.0625307
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 234,
      "eligibility_flag": false,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.35714285714285715,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality",
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:57:18Z",
      "losses": 406,
      "max_score": 59.53630433773744,
      "measured_at": null,
      "min_score": 18.568992620174647,
      "model_code_failure_rate": 0.2857142857142857,
      "model_code_failures": 4,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 950,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 5,
      "repaired_rate": 0.35714285714285715,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.591197146192016,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 310
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:qwen-qwen3-7-plus:a67ab29b6f7f0b5a",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.08827968,
        "mean": 0.03155999,
        "median": 0.01479536,
        "min": 0.00524064,
        "recorded_attempt_count": 29,
        "run_count": 17,
        "total": 0.51646592
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 336,
      "eligibility_flag": false,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.29411764705882354,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:48:47Z",
      "losses": 423,
      "max_score": 72.53293912084276,
      "measured_at": null,
      "min_score": 3.600933227553536,
      "model_code_failure_rate": 0.29411764705882354,
      "model_code_failures": 5,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1071,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 7,
      "repaired_rate": 0.4117647058823529,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.37571804749471,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 312
    },
    {
      "admitted_plugins": 43,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-5-flash-lite:1e1b77d01aa6fd1f",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 43,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 132
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.0719635,
        "mean": 0.03858281041666666,
        "median": 0.037386975,
        "min": 0.012759,
        "recorded_attempt_count": 132,
        "run_count": 48,
        "total": 1.8519748999999999
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 47,
      "draws": 1845,
      "eligibility_flag": true,
      "entry_count": 42,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-07"
      ],
      "first_pass_admitted": 36,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:51:52Z",
      "losses": 2652,
      "max_score": 73.02102977984342,
      "measured_at": null,
      "min_score": 10.571254109747576,
      "model_code_failure_rate": 0.10416666666666667,
      "model_code_failures": 5,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 6078,
      "rating_method": "sequential_elo",
      "raw_elo": 1399.0623593871992,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 7,
      "repaired_rate": 0.14583333333333334,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.35621790435424,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 1581
    },
    {
      "admitted_plugins": 27,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:deepseek-deepseek-v4-flash:fb6f94455ec4d370",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 27,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 49
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.0221782524,
        "mean": 0.005150116054583333,
        "median": 0.00311373,
        "min": 0.0013289177,
        "recorded_attempt_count": 49,
        "run_count": 32,
        "total": 0.14908945064
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 689,
      "eligibility_flag": false,
      "entry_count": 27,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 18,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "untested_or_ineligible_settings"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:23:15Z",
      "losses": 791,
      "max_score": 72.31048780319064,
      "measured_at": null,
      "min_score": 16.951008971108347,
      "model_code_failure_rate": 0.15625,
      "model_code_failures": 5,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1974,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.3301412045305,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.28125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 33.346988072989255,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 494
    },
    {
      "admitted_plugins": 23,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:poolside-laguna-s-2-1:aa9d42ace8f050f0",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 23,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 68
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.0068074,
        "mean": 0.0032179299999999995,
        "median": 0.00314426,
        "min": 0.0012446800000000002,
        "recorded_attempt_count": 68,
        "run_count": 28,
        "total": 0.09094181999999999
      },
      "codegen_evaluated_cells": 28,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 47,
      "draws": 1114,
      "eligibility_flag": false,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 4,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T00:33:40Z",
      "losses": 1117,
      "max_score": 57.87934682152756,
      "measured_at": null,
      "min_score": 19.31198981966688,
      "model_code_failure_rate": 0.17857142857142858,
      "model_code_failures": 5,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 35,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2918,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.32142857142857145,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 33.18219132607179,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 687
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:thinkingmachines-inkling-small:e5c2210ece87e3e8",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 24,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 43
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.06806129999999999,
        "mean": 0.01775885625,
        "median": 0.0102184875,
        "min": 0.00430875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 43
        },
        "recorded_attempt_count": 43,
        "run_count": 28,
        "total": 0.5373186
      },
      "codegen_evaluated_cells": 28,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 20,
      "draws": 148,
      "eligibility_flag": false,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 15,
      "first_pass_rate": 0.5357142857142857,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T05:50:12Z",
      "losses": 156,
      "max_score": 55.386274611099374,
      "measured_at": null,
      "min_score": 11.59827459432436,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 4,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 36,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 404,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.8709337229934,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.32142857142857145,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 32.998933573710495,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 100
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:minimax-minimax-m3:bb38eb0c97be722d",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.09803328,
        "mean": 0.049222395,
        "median": 0.05336871,
        "min": 0.00639384,
        "recorded_attempt_count": 30,
        "run_count": 16,
        "total": 0.7875583199999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 330,
      "eligibility_flag": false,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:33:21Z",
      "losses": 505,
      "max_score": 52.04366523994301,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 3,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 37,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1182,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.5625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 32.78696154293632,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 347
    },
    {
      "admitted_plugins": 24,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:xiaomi-mimo-v2-5:ba2faefd47e3050c",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 37,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 108
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 16,
        "max": 0.0597184625,
        "mean": 0.015888486455555555,
        "median": 0.014928570933333333,
        "min": 0.00169122,
        "recorded_attempt_count": 108,
        "run_count": 56,
        "total": 0.7524538071999999
      },
      "codegen_evaluated_cells": 36,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 1059,
      "eligibility_flag": false,
      "entry_count": 37,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.2222222222222222,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings"
      ],
      "infra_excluded_game_aliases": [
        "GB2-03",
        "GB2-06",
        "GB2-07"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:45Z",
      "losses": 1095,
      "max_score": 58.591838652401584,
      "measured_at": null,
      "min_score": 17.329198413600206,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 12,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 38,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2986,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.1023336394398,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 16,
      "repaired_rate": 0.4444444444444444,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 32.73983907587124,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 832
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:meituan-longcat-2-0:75c0c8b0e77d80fa",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 26,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 108
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.103943664,
        "mean": 0.050012701874999996,
        "median": 0.041983026,
        "min": 0.006392298,
        "recorded_attempt_count": 108,
        "run_count": 32,
        "total": 1.60040646
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 47,
      "draws": 896,
      "eligibility_flag": false,
      "entry_count": 26,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 17,
      "first_pass_rate": 0.53125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T06:50:55Z",
      "losses": 1363,
      "max_score": 55.24795980739564,
      "measured_at": null,
      "min_score": 17.33176752068492,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 6,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 39,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3095,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.28125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 32.47549452806633,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 836
    },
    {
      "admitted_plugins": 21,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:nvidia-nemotron-3-ultra-550b-a55b:14c1d11c89476159",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 21,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 70
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 13,
        "max": 0.13485595000000003,
        "mean": 0.03294963020833334,
        "median": 0.02851355,
        "min": 0.0111232,
        "recorded_attempt_count": 70,
        "run_count": 34,
        "total": 1.21164085
      },
      "codegen_evaluated_cells": 34,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 614,
      "eligibility_flag": false,
      "entry_count": 21,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.20588235294117646,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "untested_or_ineligible_settings"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:29:54Z",
      "losses": 592,
      "max_score": 61.89486875016836,
      "measured_at": null,
      "min_score": 10.490412921476183,
      "model_code_failure_rate": 0.38235294117647056,
      "model_code_failures": 13,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 40,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1589,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.4206699785475,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 14,
      "repaired_rate": 0.4117647058823529,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.88162845501124,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 383
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:stepfun-step-3-7-flash:0151b4f3ef2d8a82",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 59
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.11219570000000001,
        "mean": 0.0416694575,
        "median": 0.033877925,
        "min": 0.00984735,
        "recorded_attempt_count": 59,
        "run_count": 24,
        "total": 1.00006698
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 45,
      "draws": 318,
      "eligibility_flag": false,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-19T15:24:00Z",
      "losses": 682,
      "max_score": 52.921447482930446,
      "measured_at": null,
      "min_score": 9.651433101795904,
      "model_code_failure_rate": 0.4583333333333333,
      "model_code_failures": 11,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 41,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1425,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.5182027373544,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 10,
      "repaired_rate": 0.4166666666666667,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 30.81849785585852,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 425
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:nex-agi-nex-n2-pro:a1783d1581f6f6d9",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 12,
        "max": 0.215758025,
        "mean": 0.132049078125,
        "median": 0.1281735,
        "min": 0.061553000000000004,
        "recorded_attempt_count": 53,
        "run_count": 24,
        "total": 3.4057992500000003
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 312,
      "eligibility_flag": false,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality",
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:35:20Z",
      "losses": 431,
      "max_score": 63.528190114310334,
      "measured_at": null,
      "min_score": 13.67320578769338,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 12,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 42,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1000,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 12,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 29.567845015724004,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 257
    },
    {
      "admitted_plugins": 27,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:thinkingmachines-inkling:96d334950f7b14e7",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 27,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 145
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 21,
        "max": 0.302804525,
        "mean": 0.12502029041666668,
        "median": 0.082332765,
        "min": 0.01945095,
        "recorded_attempt_count": 145,
        "run_count": 48,
        "total": 6.00097394
      },
      "codegen_evaluated_cells": 48,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 47,
      "draws": 971,
      "eligibility_flag": false,
      "entry_count": 27,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 16,
      "first_pass_rate": 0.3333333333333333,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T23:41:33Z",
      "losses": 1496,
      "max_score": 68.95924601863939,
      "measured_at": null,
      "min_score": 6.641760874582254,
      "model_code_failure_rate": 0.4375,
      "model_code_failures": 21,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 43,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 3213,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.1972460882555,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 11,
      "repaired_rate": 0.22916666666666666,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 28.699834837367963,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 746
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:openai-gpt-oss-120b:1ff5d67f22d3eaab",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 48
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.01660212,
        "mean": 0.00430918425,
        "median": 0.0025298300000000003,
        "min": 0.00045831,
        "recorded_attempt_count": 48,
        "run_count": 24,
        "total": 0.10342042200000001
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 46,
      "draws": 665,
      "eligibility_flag": true,
      "entry_count": 19,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-05",
        "GB2-07"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T05:21:37Z",
      "losses": 1040,
      "max_score": 67.33768307109139,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.20833333333333334,
      "model_code_failures": 5,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 44,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2083,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.4697763443867,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 13,
      "repaired_rate": 0.5416666666666666,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 28.284755733249842,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 378
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:cohere-north-mini-code:a91d2017566aaf6e",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 45
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 13,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 45,
        "run_count": 24,
        "total": 0.0
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 352,
      "eligibility_flag": false,
      "entry_count": 17,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "unknown_capability_evidence",
        "missing_generation_quality",
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:19:01Z",
      "losses": 460,
      "max_score": 50.38149773221454,
      "measured_at": null,
      "min_score": 20.41646207891444,
      "model_code_failure_rate": 0.5416666666666666,
      "model_code_failures": 13,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": 45,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1058,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 5,
      "repaired_rate": 0.20833333333333334,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 26.986632490268974,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 246
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:google-gemini-3-1-flash-lite:0903ce17ebd3d72b",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 24,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 8,
        "max": 0.0422995,
        "mean": 0.014503875,
        "median": 0.010566625,
        "min": 0.003432,
        "recorded_attempt_count": 50,
        "run_count": 24,
        "total": 0.34809300000000004
      },
      "codegen_evaluated_cells": 24,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 341,
      "eligibility_flag": false,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.20833333333333334,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "untested_or_ineligible_settings"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:18:42Z",
      "losses": 704,
      "max_score": 46.38961044453501,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 8,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": 46,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 1347,
      "rating_method": "sequential_elo",
      "raw_elo": 1246.731885189902,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 11,
      "repaired_rate": 0.4583333333333333,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 25.465631974669503,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 302
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:mistralai-mistral-medium-3-5:a9c28fc18da0cc0b",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 28
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.3927285,
        "mean": 0.116635875,
        "median": 0.0747585,
        "min": 0.0223935,
        "recorded_attempt_count": 28,
        "run_count": 17,
        "total": 2.2589024999999996
      },
      "codegen_evaluated_cells": 17,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 121,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.23529411764705882,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "missing_or_non_distinct_settings",
        "untested_or_ineligible_settings",
        "missing_generation_quality",
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:49:34Z",
      "losses": 381,
      "max_score": 40.86555647776021,
      "measured_at": null,
      "min_score": 11.636247230495337,
      "model_code_failure_rate": 0.5294117647058824,
      "model_code_failures": 9,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": 47,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 694,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "openrouter",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.23529411764705882,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 24.2470324561767,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 192
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:overall:inclusionai-ling-3-0-flash:879c7abb2fdbd104",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 16,
        "cost_basis_counts": {
          "provider_reported": 92
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 15,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 92,
        "run_count": 32,
        "total": 0.0
      },
      "codegen_evaluated_cells": 31,
      "conditional_success_score": null,
      "contributing_entrants": null,
      "distinct_rated_opponents": 46,
      "draws": 861,
      "eligibility_flag": false,
      "entry_count": 22,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "aggregate",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.22580645161290322,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "missing_bracket_scores",
        "unknown_capability_evidence",
        "missing_generation_quality",
        "below_generation_quality_threshold",
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:59Z",
      "losses": 901,
      "max_score": 43.039137688291845,
      "measured_at": null,
      "min_score": 13.028496075357975,
      "model_code_failure_rate": 0.4838709677419355,
      "model_code_failures": 15,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 48,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "partial",
      "rated_matches": 2180,
      "rating_method": "sequential_elo",
      "raw_elo": null,
      "reasoning_bracket": null,
      "reasoning_level": "Overall Models",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "aggregate",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "overall"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": null,
        "reasoning_bucket": "aggregate",
        "reasoning_bucket_label": "Aggregate of public reasoning variants",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": null
      },
      "reasoning_setting": null,
      "repaired_admitted": 9,
      "repaired_rate": 0.2903225806451613,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 23.679689895531027,
      "score_basis": "mean of available official reasoning-group scores",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "overall",
      "track_name": "Overall Models",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 418
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1132,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 18,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.551725,
        "mean": 0.44617968750000003,
        "median": 0.45788,
        "min": 0.33828,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 7.138875
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 75.96881544186866,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 160,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:35:16Z",
      "losses": 187,
      "max_score": 90.23843179247481,
      "measured_at": null,
      "min_score": 51.33723880160861,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1132,
      "rating_method": "sequential_elo",
      "raw_elo": 1778.4915205310851,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 73.47462325689973,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 785
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 690,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 37,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.24740375,
        "mean": 0.229063125,
        "median": 0.23243875,
        "min": 0.20046375,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.832505
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 66.4740090857523,
      "contributing_entrants": null,
      "distinct_rated_opponents": 21,
      "draws": 98,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T05:21:14Z",
      "losses": 149,
      "max_score": 90.14837149543118,
      "measured_at": null,
      "min_score": 36.8828822319936,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 690,
      "rating_method": "sequential_elo",
      "raw_elo": 1673.4699526261174,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 66.4740090857523,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 443
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 528,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.6981,
        "mean": 0.5046499999999999,
        "median": 0.511355,
        "min": 0.33027,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 4.0372
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.30128747589305,
      "contributing_entrants": null,
      "distinct_rated_opponents": 35,
      "draws": 57,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:34:24Z",
      "losses": 117,
      "max_score": 77.40648648738761,
      "measured_at": null,
      "min_score": 56.05592222052655,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 524,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.1776756435243,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 66.05883395789598,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 350
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 746,
      "canonical_public_row_identity": "publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 9,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "max": 0.0878628,
        "mean": 0.0635932,
        "median": 0.06199639999999999,
        "min": 0.0498884,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.5087456
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 57.180934977713015,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 170,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:42:30Z",
      "losses": 208,
      "max_score": 87.21199208118166,
      "measured_at": null,
      "min_score": 28.15047326894219,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 744,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.1880129737476,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 57.180934977713015,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 366
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1813,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 120,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 44
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.3888165,
        "mean": 0.26060548125,
        "median": 0.24728879999999998,
        "min": 0.17802225,
        "recorded_attempt_count": 44,
        "run_count": 16,
        "total": 4.1696877
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 57.72594535990394,
      "contributing_entrants": null,
      "distinct_rated_opponents": 45,
      "draws": 443,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-08"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:38:44Z",
      "losses": 428,
      "max_score": 90.59930630959718,
      "measured_at": null,
      "min_score": 16.174375669656794,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1813,
      "rating_method": "sequential_elo",
      "raw_elo": 1648.3308135308127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 55.83069925202183,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 942
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 638,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 60,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "max": 0.5145615,
        "mean": 0.34875300000000004,
        "median": 0.335163,
        "min": 0.254883,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 2.7900240000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 55.362830501043646,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 195,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:04:12Z",
      "losses": 156,
      "max_score": 84.5317048418163,
      "measured_at": null,
      "min_score": 26.743400089025748,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 636,
      "rating_method": "sequential_elo",
      "raw_elo": 1614.7519290982523,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 55.362830501043646,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 285
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 730,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 59,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.4120425,
        "mean": 0.283374375,
        "median": 0.26543625,
        "min": 0.2124125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 2.266995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 54.95759913349221,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 211,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:23:52Z",
      "losses": 170,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 25.90894221037543,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 730,
      "rating_method": "sequential_elo",
      "raw_elo": 1626.7886478001333,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 54.95759913349221,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 349
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 676,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 103,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.58673,
        "mean": 0.44285687500000004,
        "median": 0.4176025,
        "min": 0.34269,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 3.5428550000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.08734861096748,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 224,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:43:10Z",
      "losses": 187,
      "max_score": 73.85605709393225,
      "measured_at": null,
      "min_score": 37.548190679008606,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 676,
      "rating_method": "sequential_elo",
      "raw_elo": 1585.936213398567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 53.08734861096748,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 265
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 597,
      "canonical_public_row_identity": "publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 24,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.060198249999999995,
        "mean": 0.047021,
        "median": 0.04824225,
        "min": 0.0324825,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.37616800000000006
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 54.56046464326638,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 135,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T02:44:09Z",
      "losses": 156,
      "max_score": 79.71591004614217,
      "measured_at": null,
      "min_score": 28.93634004616261,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": 0.875,
      "provider": "Other",
      "provider_key": "other",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 597,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.5345465563753,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 52.76914693309831,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 306
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1188,
      "canonical_public_row_identity": "publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 147,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "max": 0.4398702,
        "mean": 0.29041619999999996,
        "median": 0.301782,
        "min": 0.095232,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 16
        },
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 2.3233296
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.63127725653765,
      "contributing_entrants": null,
      "distinct_rated_opponents": 41,
      "draws": 376,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T07:54:09Z",
      "losses": 385,
      "max_score": 68.46351429427254,
      "measured_at": null,
      "min_score": 20.275423642118344,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 1.0,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1177,
      "rating_method": "sequential_elo",
      "raw_elo": 1526.909059018083,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 47.63127725653765,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 416
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 670,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 97,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.34174499999999997,
        "mean": 0.217940625,
        "median": 0.19638,
        "min": 0.14813,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.743525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 47.42768341066297,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 266,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:49:27Z",
      "losses": 166,
      "max_score": 80.14817108632784,
      "measured_at": null,
      "min_score": 15.975113871358344,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 670,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.8421897562828,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 47.42768341066297,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 238
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 725,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 49,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.325659,
        "mean": 0.25189603125,
        "median": 0.25775625,
        "min": 0.169101,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 2.01516825
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.81264427076511,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 219,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:55:18Z",
      "losses": 217,
      "max_score": 58.26867546532442,
      "measured_at": null,
      "min_score": 21.89947442115403,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 723,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.8496538432216,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 46.81264427076511,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 287
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 566,
      "canonical_public_row_identity": "publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.072978,
        "mean": 0.048872,
        "median": 0.046325000000000005,
        "min": 0.037309999999999996,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.39097600000000005
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.20675055685002,
      "contributing_entrants": null,
      "distinct_rated_opponents": 37,
      "draws": 143,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:17:46Z",
      "losses": 185,
      "max_score": 62.569827155594346,
      "measured_at": null,
      "min_score": 36.401476747289344,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.2514541628454,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 46.72264602793167,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 238
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 566,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 106,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.08827968,
        "mean": 0.05437612,
        "median": 0.0574344,
        "min": 0.00733824,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.43500896
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.749573048252884,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 176,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:48:47Z",
      "losses": 188,
      "max_score": 72.53293912084276,
      "measured_at": null,
      "min_score": 22.584554928424122,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": 0.75,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.7798004283432,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 43.50537983965268,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 202
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 700,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.24673750000000003,
        "mean": 0.16744,
        "median": 0.15809499999999999,
        "min": 0.108735,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 1.33952
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.44652688282063,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 259,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:18:32Z",
      "losses": 212,
      "max_score": 60.64978060082346,
      "measured_at": null,
      "min_score": 21.8994809309449,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 700,
      "rating_method": "sequential_elo",
      "raw_elo": 1498.9152130042207,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 43.44652688282063,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 229
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 494,
      "canonical_public_row_identity": "publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 73,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "max": 0.14831665,
        "mean": 0.06589574925,
        "median": 0.044104765,
        "min": 0.0155414,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.5271659940000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.245062052265894,
      "contributing_entrants": null,
      "distinct_rated_opponents": 36,
      "draws": 195,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T03:34:47Z",
      "losses": 138,
      "max_score": 66.27613202821979,
      "measured_at": null,
      "min_score": 19.216835075427902,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 494,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.3698922933597,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 43.245062052265894,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 560,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 67,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.21477374999999999,
        "mean": 0.17756265624999998,
        "median": 0.17285124999999998,
        "min": 0.1418975,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 1.42050125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.25870820023652,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 156,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:19:06Z",
      "losses": 204,
      "max_score": 62.86088508787239,
      "measured_at": null,
      "min_score": 21.501856921354634,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 560,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.5946476760857,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.80561559285842,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 652,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 99,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.12185499999999999,
        "mean": 0.09110296875000001,
        "median": 0.09280125,
        "min": 0.0343775,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.7288237499999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 44.10198903600353,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 240,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:35:11Z",
      "losses": 203,
      "max_score": 79.13676897206143,
      "measured_at": null,
      "min_score": 15.302941621960535,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": 0.875,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 652,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.7786636926899,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.65404179929354,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 209
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 572,
      "canonical_public_row_identity": "publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 12,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.226689264,
        "mean": 0.16037539425,
        "median": 0.140728509,
        "min": 0.10689655,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 1.283003154
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 45.58338513665577,
      "contributing_entrants": null,
      "distinct_rated_opponents": 37,
      "draws": 163,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-06"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:26:41Z",
      "losses": 193,
      "max_score": 63.086489595554106,
      "measured_at": null,
      "min_score": 23.435946683398193,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": 0.75,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 572,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.8922747479967,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.42011970249428,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 216
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 675,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.08884,
        "mean": 0.06562375000000001,
        "median": 0.062855,
        "min": 0.049908,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.5249900000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.94075981647538,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 200,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T07:22:40Z",
      "losses": 266,
      "max_score": 52.37264260162897,
      "measured_at": null,
      "min_score": 28.897713502544164,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 675,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.073920575025,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 40.94075981647538,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 209
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 689,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 69,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.011164349999999998,
        "mean": 0.00631805625,
        "median": 0.005847,
        "min": 0.00434295,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 0.05054445
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.169901679730685,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 217,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:38:55Z",
      "losses": 268,
      "max_score": 61.35124581231818,
      "measured_at": null,
      "min_score": 25.07186922308482,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 688,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.6454918534998,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 40.169901679730685,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 203
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1028,
      "canonical_public_row_identity": "publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 72,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 25
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.034210525000000006,
        "mean": 0.024715571875,
        "median": 0.0256067375,
        "min": 0.01676735,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 25
        },
        "run_count": 16,
        "token_priced_attempt_count": 25,
        "total": 0.39544915
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 42.61298325940131,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 200,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T06:55:07Z",
      "losses": 416,
      "max_score": 63.14422335372282,
      "measured_at": null,
      "min_score": 15.136633992883711,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1026,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.270076244519,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 39.655849282035284,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 410
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 726,
      "canonical_public_row_identity": "publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 104,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "max": 0.07439860000000001,
        "mean": 0.060660574999999994,
        "median": 0.0565846,
        "min": 0.0485456,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.48528459999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.4814143462601,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 276,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:34:43Z",
      "losses": 241,
      "max_score": 67.9767252117913,
      "measured_at": null,
      "min_score": 21.895370370120215,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 726,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.375862707454,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 8,
      "repaired_rate": 1.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 39.4814143462601,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 209
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 621,
      "canonical_public_row_identity": "publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 109,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00444719,
        "mean": 0.0024656575,
        "median": 0.002155255,
        "min": 0.0011302579999999999,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.019725259999999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.76717792204459,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 284,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-07"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:12:06Z",
      "losses": 203,
      "max_score": 46.6367117182378,
      "measured_at": null,
      "min_score": 21.69349452538362,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 621,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.7193844748713,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 35.560045662536105,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 0.0
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.059131406213616,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 170,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:19:01Z",
      "losses": 228,
      "max_score": 50.38149773221454,
      "measured_at": null,
      "min_score": 27.8658776184786,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 566,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.9769156979073,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 33.55680290162351,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 168
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1338,
      "canonical_public_row_identity": "publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 102,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 52
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.03062629,
        "mean": 0.020124273158333334,
        "median": 0.017895481666666668,
        "min": 0.012095886733333333,
        "recorded_attempt_count": 52,
        "run_count": 24,
        "total": 0.486187507
      },
      "codegen_evaluated_cells": 12,
      "conditional_success_score": 35.76399551847051,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 486,
      "eligibility_flag": true,
      "entry_count": 15,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.08333333333333333,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-03",
        "GB2-06",
        "GB2-07"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:57:10Z",
      "losses": 509,
      "max_score": 44.220775294483815,
      "measured_at": null,
      "min_score": 22.699064906311374,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 4,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.6666666666666666,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1338,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.8378305178246,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 7,
      "repaired_rate": 0.5833333333333334,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 32.31641800758346,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 343
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 928,
      "canonical_public_row_identity": "publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 164,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.004911942999999999,
        "mean": 0.0031858331662499998,
        "median": 0.002947833025,
        "min": 0.001831717,
        "recorded_attempt_count": 24,
        "run_count": 16,
        "total": 0.05097333066
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 33.18602349106142,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 328,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 10,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T20:22:51Z",
      "losses": 381,
      "max_score": 45.206404703543946,
      "measured_at": null,
      "min_score": 16.951008971108347,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 928,
      "rating_method": "sequential_elo",
      "raw_elo": 1400.4522087437192,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 32.09646694130927,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 219
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1810,
      "canonical_public_row_identity": "publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 113,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 70
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.103943664,
        "mean": 0.0866474535,
        "median": 0.088847748,
        "min": 0.062759676,
        "recorded_attempt_count": 70,
        "run_count": 16,
        "total": 1.3863592560000002
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 33.374227954450966,
      "contributing_entrants": null,
      "distinct_rated_opponents": 41,
      "draws": 425,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T10:07:05Z",
      "losses": 873,
      "max_score": 45.093217679579666,
      "measured_at": null,
      "min_score": 19.52045526776426,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1787,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.5200443945464,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 3,
      "repaired_rate": 0.1875,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.058218703193194,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 23,
      "wins": 489
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 424,
      "canonical_public_row_identity": "publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:7859dde46c855271",
      "capped_draws": 83,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 21
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.065385,
        "mean": 0.03551179375,
        "median": 0.032728425,
        "min": 0.0200767,
        "recorded_attempt_count": 21,
        "run_count": 9,
        "total": 0.3177278
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 34.48811830245897,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 162,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-05"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:41:43Z",
      "losses": 150,
      "max_score": 61.89486875016836,
      "measured_at": null,
      "min_score": 12.425400361217248,
      "model_code_failure_rate": 0.4444444444444444,
      "model_code_failures": 4,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.5555555555555556,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 424,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.4738225118065,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 5,
      "repaired_rate": 0.5555555555555556,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 29.774972792271555,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 112
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 576,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 78,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0149315,
        "mean": 0.0101355,
        "median": 0.010566625,
        "min": 0.00402875,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 0.081084
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.650057773456513,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 141,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:18:42Z",
      "losses": 284,
      "max_score": 45.60739618718008,
      "measured_at": null,
      "min_score": 0.5096881306947669,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 574,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.1129772607046,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 29.453697554840808,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 149
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 1711,
      "canonical_public_row_identity": "publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 270,
      "codegen_cost_usd": {
        "admitted_cell_count": 11,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0068074,
        "mean": 0.0034371900000000006,
        "median": 0.00326368,
        "min": 0.00211404,
        "recorded_attempt_count": 35,
        "run_count": 14,
        "total": 0.04917796000000001
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 30.09277970422465,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 691,
      "eligibility_flag": true,
      "entry_count": 11,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-07"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T03:23:43Z",
      "losses": 709,
      "max_score": 39.37852779468735,
      "measured_at": null,
      "min_score": 21.375448760554548,
      "model_code_failure_rate": 0.21428571428571427,
      "model_code_failures": 3,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": 0.7857142857142857,
      "provider": "Other",
      "provider_key": "other",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1709,
      "rating_method": "sequential_elo",
      "raw_elo": 1361.8687133027288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 4,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 28.332080574852135,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 309
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 658,
      "canonical_public_row_identity": "publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 88,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.09705768000000001,
        "mean": 0.0730637925,
        "median": 0.07051098,
        "min": 0.05225028,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.58451034
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 28.93797267122631,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 211,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:04:06Z",
      "losses": 307,
      "max_score": 47.83708028920805,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": 0.875,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 658,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.808399935368,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 7,
      "repaired_rate": 0.875,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 27.987887233331772,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 140
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 424,
      "canonical_public_row_identity": "publication-row.v1:balanced:nex-agi-nex-n2-pro:bfccd9446404db2c",
      "capped_draws": 16,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.13491350000000002,
        "mean": 0.10247140625000001,
        "median": 0.113468875,
        "min": 0.061553000000000004,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 0.81977125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 31.221768608847007,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 51,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:35:20Z",
      "losses": 257,
      "max_score": 48.573486962202864,
      "measured_at": null,
      "min_score": 13.67320578769338,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": 0.625,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": 33,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 424,
      "rating_method": "sequential_elo",
      "raw_elo": 1331.2285539260201,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 27.76051413105611,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 2061,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 296,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 48
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0481474,
        "mean": 0.03800683125,
        "median": 0.037386975,
        "min": 0.02957195,
        "recorded_attempt_count": 48,
        "run_count": 16,
        "total": 0.6081093000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.967008360684986,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 680,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:23:52Z",
      "losses": 995,
      "max_score": 40.402427775346794,
      "measured_at": null,
      "min_score": 14.602532202469558,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 34,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2052,
      "rating_method": "sequential_elo",
      "raw_elo": 1326.5708080896875,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 27.048801419001688,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 377
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1276,
      "canonical_public_row_identity": "publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 65,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.266665,
        "mean": 0.20888499999999996,
        "median": 0.20905875000000002,
        "min": 0.14104,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8,
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 3.34216
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.33568653113013,
      "contributing_entrants": null,
      "distinct_rated_opponents": 46,
      "draws": 324,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-21T15:41:46Z",
      "losses": 389,
      "max_score": 84.27791783076424,
      "measured_at": null,
      "min_score": 22.36064210907722,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1275,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.9183033568818,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 52.33568653113013,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 562
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 464,
      "canonical_public_row_identity": "publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:2437b68c7c28667e",
      "capped_draws": 66,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 17
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.2996388,
        "mean": 0.13471628689999998,
        "median": 0.1144847257,
        "min": 0.027613287599999998,
        "recorded_attempt_count": 17,
        "run_count": 8,
        "total": 1.0777302951999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.17892461527247,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 110,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:01Z",
      "losses": 186,
      "max_score": 68.98589007065465,
      "measured_at": null,
      "min_score": 31.43712263783562,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": 0.75,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 464,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.9451099086941,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.974331635082116,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 168
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 11,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "evidence_basis": "Provider-reported",
        "max": 0.25803,
        "mean": 0.104435,
        "median": 0.081263,
        "min": 0.075542,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.83548
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.089605395034724,
      "contributing_entrants": null,
      "distinct_rated_opponents": 16,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T05:21:47Z",
      "losses": 41,
      "max_score": 55.331168423892514,
      "measured_at": null,
      "min_score": 11.831462426203206,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1528.0240200539201,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 40.089605395034724,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 394,
      "canonical_public_row_identity": "publication-row.v1:balanced:google-gemma-4-31b-it:d0c0442b34151c5a",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0092087,
        "mean": 0.006571171428571429,
        "median": 0.00666192,
        "min": 0.00456754,
        "recorded_attempt_count": 15,
        "run_count": 7,
        "total": 0.0459982
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 43.751461488092524,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-01"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:57:18Z",
      "losses": 171,
      "max_score": 59.53630433773744,
      "measured_at": null,
      "min_score": 37.24500604167221,
      "model_code_failure_rate": 0.42857142857142855,
      "model_code_failures": 3,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": 0.5714285714285714,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 392,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.1502970457288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": 4,
      "repaired_rate": 0.5714285714285714,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 38.039346973942585,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 155
    },
    {
      "admitted_plugins": 26,
      "attempted_matches": 309,
      "canonical_public_row_identity": "publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 21,
      "codegen_cost_usd": {
        "admitted_cell_count": 26,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 39,
        "run_count": 30,
        "total": 0.0
      },
      "codegen_evaluated_cells": 30,
      "conditional_success_score": 35.15050484430993,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": 21,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-06"
      ],
      "first_pass_admitted": 21,
      "first_pass_rate": 0.7,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T14:12:11Z",
      "losses": 133,
      "max_score": 42.84271453304636,
      "measured_at": null,
      "min_score": 10.044999300170076,
      "model_code_failure_rate": 0.13333333333333333,
      "model_code_failures": 4,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": 0.8666666666666667,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.8848485365963,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.16666666666666666,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 33.91521622287523,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-row.v1:balanced:stepfun-step-3-7-flash:efafeb77b13aa96b",
      "capped_draws": 0,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0711619,
        "mean": 0.039345212500000004,
        "median": 0.033877925,
        "min": 0.02387735,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.3147617
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 38.412835389657154,
      "contributing_entrants": null,
      "distinct_rated_opponents": 37,
      "draws": 137,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:10Z",
      "losses": 139,
      "max_score": 51.477038427166434,
      "measured_at": null,
      "min_score": 23.01907317579323,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.5,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.29805301024,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 4,
      "repaired_rate": 0.5,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 32.301215578893725,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 92
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 15,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.01196465,
        "mean": 0.00854730625,
        "median": 0.008640199999999999,
        "min": 0.00555765,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 15
        },
        "recorded_attempt_count": 15,
        "run_count": 9,
        "total": 0.07763974999999998
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 32.80838268685741,
      "contributing_entrants": null,
      "distinct_rated_opponents": 16,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.4444444444444444,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:02:59Z",
      "losses": 62,
      "max_score": 47.504378523447755,
      "measured_at": null,
      "min_score": 14.229198182783765,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.7212148548156,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 4,
      "repaired_rate": 0.4444444444444444,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.856399674988566,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 793,
      "canonical_public_row_identity": "publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 126,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 10,
        "max": 0.11839474,
        "mean": 0.07845433000000002,
        "median": 0.08046371000000001,
        "min": 0.036046930000000005,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 1.25526928
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 31.522734372110563,
      "contributing_entrants": null,
      "distinct_rated_opponents": 45,
      "draws": 237,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T12:49:16Z",
      "losses": 384,
      "max_score": 57.38467373838492,
      "measured_at": null,
      "min_score": 6.641760874582254,
      "model_code_failure_rate": 0.625,
      "model_code_failures": 10,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.375,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 793,
      "rating_method": "sequential_elo",
      "raw_elo": 1345.466508725796,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 24.66787274376822,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 172
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-row.v1:balanced:inclusionai-ling-3-0-flash:6f99584b1bad82dc",
      "capped_draws": null,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 52
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 52,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 15,
      "conditional_success_score": 27.4134235117906,
      "contributing_entrants": null,
      "distinct_rated_opponents": 41,
      "draws": 254,
      "eligibility_flag": false,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.06666666666666667,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold",
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-05"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T10:20:46Z",
      "losses": 493,
      "max_score": 43.039137688291845,
      "measured_at": null,
      "min_score": 13.028496075357975,
      "model_code_failure_rate": 0.6,
      "model_code_failures": 9,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": 0.4,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 974,
      "rating_method": "sequential_elo",
      "raw_elo": 1373.342805247122,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": 5,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 21.801093294221513,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": null,
      "unilateral_faults": null,
      "wins": 227
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-19T23:51:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 2032.611031916279,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1889.6728264013168,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 84.5317048418163,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-20T01:48:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1837.8230227206066,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 79.71591004614217,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-03T18:34:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1798.3560336460778,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 75.63550927040828,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 2,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-03T18:12:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1746.7718654981127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 69.68374424625355,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 2,
      "wins": 49
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 87,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1733.9815154005573,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.96857780411901,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.993443214731016,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 228,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1716.4746501562718,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.61223768430166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.902777777777777,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 139,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-20T02:13:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 132,
      "rating_method": "sequential_elo",
      "raw_elo": 1704.7601387652967,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 66.80663569310781,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-19T23:37:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1656.0651074364548,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.974479549744906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 56,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1638.442124593186,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.10237984120693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-03T16:16:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.9382025233147,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.26867546532442,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 2,
      "wins": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 45,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 45,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-19T23:49:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.458566001231,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.02925130550037,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 89,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-20T02:03:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 89,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.7387010272973,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.24671194156034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.954627669472988,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-04T20:42:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.6558361046946,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.96146347343779,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-08-03T09:57:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.8769477318842,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.75703593114919,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:7859dde46c855271",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-03T02:39:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.0881129608072,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.6769093213218,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-03T14:29:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.8516420385984,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.549073450674925,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-03T14:22:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.2412310238194,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.395710077391875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.2955239513867,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.91721529100322,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-03T14:21:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1490.1750231054355,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.773386925532954,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-23T12:28:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1530.420159897876,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.69013350806352,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-05T02:21:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.0985357998015,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.208769238182654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-07-31T01:08:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.6116867747367,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.118148020938065,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 85,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-19T03:12:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 85,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.5112502726618,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.887590399986145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.16638660171921,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 352,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 137,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 149,
      "max_score": null,
      "measured_at": "2026-08-22T19:58:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 352,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.289152623251,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.402427775346794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 138
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-22T16:31:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.6122502478056,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.66966887583633,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-08-22T19:58:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.1200705128342,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.37852779468735,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-05T04:12:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.8660097244824,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.24390988896453,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 65,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-07-31T02:19:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1397.2125499308513,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.46949800381537,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.23082238610738,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 130,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-08-15T02:21:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.0621525194288,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.17571462476984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 190,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 88,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 97,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1366.4931344086308,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.194844980833093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.33305067329769,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-08-05T02:21:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1318.6106318223515,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.18114898717137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.83081881614,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.776223890208286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:11:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.7786038469053,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.501856921354634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:inclusionai-ling-3-0-flash:6f99584b1bad82dc",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 15,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-08-20T01:50:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1255.2978439767162,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.281722008614956,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.463945712701573,
      "unilateral_faults": null,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1214.7994373479398,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 15.302941621960535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 82,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 109,
      "max_score": null,
      "measured_at": "2026-08-05T03:22:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1214.2842678515308,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 15.136633992883711,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.22239302669203,
      "unilateral_faults": 2,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-04T02:44:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1673.7931137310256,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 64.79913198095714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 2,
      "wins": 31
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-03T12:23:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1668.274080690368,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.392777513578906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 40,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1626.3155963816746,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 54.52715766883468,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-03T09:39:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.48401992745,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.26540457323291,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-23T06:52:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1517.6444248483235,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.110695747971825,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 67,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-19T23:36:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 67,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.022713465008,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.93634004616261,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.883906259083243,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-15T01:46:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.7378064158515,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.897713502544164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-02T23:10:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.3810335953954,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.15047326894219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-03T01:05:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1499.2755505440737,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.743400089025748,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 77,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-19T21:54:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 77,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.2440690369426,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.90894221037543,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.86385170722978,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-15T01:43:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.559288564265,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.109111227556788,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.9100862300777,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.435946683398193,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:stepfun-step-3-7-flash:efafeb77b13aa96b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-03T09:30:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.1945310202682,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.01907317579323,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 105,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 103,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-22T08:45:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 105,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.5153667728528,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.719387636610737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.8142931178632065,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 102,
      "draws": 195,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-03T04:42:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.799645643289,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.699064906311374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.033447808085375,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.2479095839017,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.584554928424122,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 130,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 118,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-19T21:55:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 130,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.0049313514542,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.36064210907722,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 67,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-03T10:43:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.1788100994386,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.8994809309449,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-03T12:16:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.896463396586,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.89947442115403,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-03T12:16:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.9758894809659,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.895370370120215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-03T12:15:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.2560006314968,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.69349452538362,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.8595823514117,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.54178243508168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 234,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "draws": 223,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-23T03:23:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 232,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.6231620188373,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.375448760554548,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-22T07:54:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1464.1282589545453,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.275423642118344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-03T03:19:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.43993039221,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.68138864924798,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.9086495306929,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.216835075427902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:7859dde46c855271",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-03T04:41:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.4123886391003,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.398846802778316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 58,
      "draws": 100,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.919888631724,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.951008971108347,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.37252890985009,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-03T14:15:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.7870290620301,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.174375669656794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-03T05:47:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.9211674035894,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 15.975113871358344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 11,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-23T00:33:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.9154364994188,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 14.229198182783765,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:inclusionai-ling-3-0-flash:6f99584b1bad82dc",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 9,
      "draws": 95,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-19T21:57:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.0330816696924,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 13.028496075357975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 38.47986322289016,
      "unilateral_faults": null,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.173692393705,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 11.831462426203206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.162820902962,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 10.044999300170076,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-03T08:16:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.731839146371,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 9.522795772569406,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-05T04:20:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1810.7920166159938,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 90.23843179247481,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.888824360518605,
      "unilateral_faults": 0,
      "wins": 112
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-21T11:42:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1643.4933772800982,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.46351429427254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-08-21T15:52:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.1519271610578,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.15840316174446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-08-22T12:02:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1565.2792867639394,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.38467373838492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.9713595499957961,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1568.0355049211498,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.34552410919058,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-21T11:43:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.6194374124107,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.664178268995066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-21T04:34:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.1018206087042,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.23562494881364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 101,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.6464217020275,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.783597464425156,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.2220869120796065,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-05T05:42:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.5686533652022,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.956517411641435,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-31T02:50:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.2149280033655,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.206404703543946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-21T09:13:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.5878420683082,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.093217679579666,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.3068886929552,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.78614708777877,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 73,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 40,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 73,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.5678575239842,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.7743274862355,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.373819371909642,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 25,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-23T14:10:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 24,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.4080832752197,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.84271453304636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 94.92504905630729,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-08-23T08:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.8365938246095,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.7632763142804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-21T15:54:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.3734345802525,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.37834288379551,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-08-22T14:30:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.2573394100423,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.4983370246016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 33,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-03T10:31:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.3652413928949,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.87335695062395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-23T02:31:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.9877282935317,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.667892968316686,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 91,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-08-23T05:19:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 91,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.518054717542,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.36327550240593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.378603514268699,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 271,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 22,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 116,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-08-23T08:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 271,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.6859481766683,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.88817423342006,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-05T00:30:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.9342129195318,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.11887554806834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-03T11:59:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.8225277095194,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.548190679008606,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 306,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 112,
      "draws": 125,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-08-23T03:05:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 306,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.4802666018688,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.33064329629842,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:nex-agi-nex-n2-pro:bfccd9446404db2c",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 27,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-04T08:55:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.0159683307136,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.28796962477342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-03T12:01:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.1877638819335,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.72802275090764,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-31T02:57:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.6979199994657,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.19952060625756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 54,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T01:53:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.2862829940107,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.9585259455821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 13,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:21:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.4114294677433,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.834909047409482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 56.49112594673751,
      "unilateral_faults": null,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1805.933180290257,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 90.14837149543118,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-05T01:23:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.1701606113888,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.05592222052655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-05T04:04:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.9623544152807,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.05762102524152,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 87,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.2200909613516,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.33723880160861,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.552760371103872,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:2437b68c7c28667e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1553.5411300031487,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.930917233328884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-05T05:04:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1550.6279522740244,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.89782707711206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.3585485416486,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.747585899586106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:stepfun-step-3-7-flash:efafeb77b13aa96b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.768886248649,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.188981149238096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-05T02:15:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.0990916013604,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.844934191198654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-05T04:03:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.6460224672696,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.846681213455774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:04:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.092051220334,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.265005107407845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 131,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 88,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 127,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.0663571860498,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.21132135718317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.444173824159213,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.404650141681,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.00273303004231,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-04T03:46:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.7535575112174,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.723688617519116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 2,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.431367332239,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.48658634194338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-05T05:10:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.6292037741962,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.29925429844576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.9213014671434,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.788828941639004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-05T00:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.5305327733142,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.50807424575855,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-03T14:28:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.1158867823526,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.477544864233046,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-05T03:15:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.5093095901468,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.31546308499324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 237,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 183,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-22T14:13:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 228,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.048880995099,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.2343034850068,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.1764504826757323,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-22T11:33:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.013285163808,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.75702900741598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 117,
      "draws": 185,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-03T11:50:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.5662869913588,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.80204674868615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.371699375400315,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemma-4-31b-it:d0c0442b34151c5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-04T02:50:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.117049186159,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.777956524978244,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 2,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-22T11:33:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.7988288950792,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.42221478251373,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.707966398987,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.34375399192475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 239,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 106,
      "draws": 172,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-21T20:33:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 239,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.8314186207444,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.87160934044171,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.0706571305287857,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-05T03:14:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.309058381632,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.81825538042852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 28,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T01:16:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.12603505286,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.61467322762245,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 29.395347377897878,
      "unilateral_faults": null,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-03T11:49:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.678974566677,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.401476747289344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-23T12:27:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.2014764650874,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.153932317419596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.127962983689,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.834147059507195,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T01:17:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.2230735526018,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.63241298761103,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:inclusionai-ling-3-0-flash:6f99584b1bad82dc",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 22,
      "draws": 125,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-22T04:21:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1437.5231110068432,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.571165805690754,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.245072352269222,
      "unilateral_faults": null,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-23T08:02:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.799314323205,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.638698369369212,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-21T20:10:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.9628271566362,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.086249261383635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 40,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-22T06:20:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.4147451259803,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.362656163193495,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-22T04:21:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.7939198480567,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.2012319421299,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-22T06:20:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.2834532411562,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.523140403424865,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 277,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 102,
      "draws": 147,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-08-23T06:52:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 254,
      "rating_method": "sequential_elo",
      "raw_elo": 1340.7970382156996,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.52045526776426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.2375081760512119,
      "unilateral_faults": 23,
      "wins": 19
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1911.2358757943127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 86.25800515426019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.823251170389485,
      "unilateral_faults": 0,
      "wins": 164
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1852.929717172452,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 81.15458170352487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-22T11:11:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1818.8752339259834,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 78.10288928195592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 308,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 124,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-08-23T02:44:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 308,
      "rating_method": "sequential_elo",
      "raw_elo": 1774.4665174138186,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 74.96104522556831,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 231
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1723.253047437652,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 69.3382874498687,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-05T05:34:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1702.4608950678553,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.9767252117913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-04T21:09:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1664.3804338059472,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 64.57296544365413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-05T02:01:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1658.3798253586838,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.81899142309433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1624.9915664363414,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.302135745250496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-05T03:41:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1631.1656521686612,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.28160282112335,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-08-05T03:41:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1620.8423835031147,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.64978060082346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemma-4-31b-it:d0c0442b34151c5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1605.3603699693099,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.53630433773744,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.875240412015687,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.103283115645,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.168257240229266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-08-05T03:49:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.5207424969149,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.367379627273316,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 84,
      "max_score": null,
      "measured_at": "2026-08-20T05:12:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.330410553067,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.18889318674271,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:42:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1578.6612634811117,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.98624033015518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-05T04:51:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.6242718976087,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.75082800967719,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-07-31T00:59:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.2082474431916,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.586976538895975,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-05T02:08:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.4972105951804,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.42159236209911,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-20T12:14:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.3039721739203,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.7884886977324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 103
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-08-05T03:00:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1562.335337787397,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.69921153212445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-23T02:44:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.9118638803197,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.62541697170394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 89,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-08-05T04:42:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 180,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.5178969518408,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.353895713407034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.137645938622816,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 11,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.8596132907571,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.94363834256713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:stepfun-step-3-7-flash:efafeb77b13aa96b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-05T02:51:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.671430011153,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.477038427166434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-05T02:08:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.9526866740612,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.38149773221454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 24.160953931632804,
      "unilateral_faults": null,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-23T07:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.077411720965,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.140227782544386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 93,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.579607297685,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.23068051946542,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-08-05T01:10:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.9826435606906,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.6367117182378,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 121,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 185,
      "max_score": null,
      "measured_at": "2026-08-22T11:34:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.4869964909099,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.451721920222965,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 220,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 122,
      "max_score": null,
      "measured_at": "2026-08-04T22:17:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 220,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.0571045642391,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.220775294483815,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.8006943798126125,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.7474591280127,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.44275909587383,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 365,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 133,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 243,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 365,
      "rating_method": "sequential_elo",
      "raw_elo": 1315.0698482131118,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.528261127510206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-20T12:25:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1365.410320453481,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.01400834375168,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:2437b68c7c28667e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-08-05T03:42:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1302.4616251701777,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.506339570901225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:nex-agi-nex-n2-pro:bfccd9446404db2c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-04T09:17:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1301.139212875865,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.279757091350554,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 75,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-07-31T03:33:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.428283867453,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.079789578479307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.60765757439077,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 77,
      "max_score": null,
      "measured_at": "2026-08-05T04:51:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.1782378757614,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.86430103882667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-08-04T21:09:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1207.2298320637442,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.847704758895738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 320,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 253,
      "max_score": null,
      "measured_at": "2026-08-22T12:02:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 320,
      "rating_method": "sequential_elo",
      "raw_elo": 1129.252871556389,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.90861104944561,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-08-04T23:59:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 935.9987215696694,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 113,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1964.5138371126773,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 90.59930630959718,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 257
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-22T11:41:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1895.3746720098352,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 84.06596764154368,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-03T12:16:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1886.2628217788806,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 82.8497697558789,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-03T08:42:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1852.9315796761991,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 80.14817108632784,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-03T10:57:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1820.3562853548483,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 77.40648648738761,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-03T07:40:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1761.3115017129503,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.53293912084276,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:2437b68c7c28667e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-03T05:25:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1715.7619684800297,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.98589007065465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-20T21:54:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1673.0845945046149,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 66.35935969494538,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-07-30T23:51:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1695.5081693751965,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 66.27613202821979,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-05T06:55:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1646.3542719474497,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.14422335372282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:7859dde46c855271",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-08-05T03:41:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.8708605783158,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.89486875016836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-22T22:29:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 91,
      "rating_method": "sequential_elo",
      "raw_elo": 1625.7147784478864,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.35124581231818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.378603514268699,
      "unilateral_faults": 1,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1615.8418485040806,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.61195345345551,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-05T03:57:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.9544501736414,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.12787105389861,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-05T05:03:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1604.3099870611559,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.56864288533566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-05T01:53:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.603307582626,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.42832822067658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.7715708378887,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.331168423892514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T04:57:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.379331282502,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.05565583214185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-08-20T18:11:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1511.5889769331868,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.8069765902766,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-03T09:49:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.81989412051,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.66745425520703,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-05T04:57:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.828057804587,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.816521510440936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-08-03T12:10:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.244562486499,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.30821047229321,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.1728462442638,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.62272982536658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-08-03T10:58:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.619465594597,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.60739618718008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-08-05T01:46:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.1489778493396,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.547794543772895,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-08-05T04:57:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1359.647741311623,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.30072691137755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 111,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 70,
      "max_score": null,
      "measured_at": "2026-08-04T20:06:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 111,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.3710022776015,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.6741764977918,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.4955591261534025,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-23T12:15:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.7352199144916,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.40170202397549,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemma-4-31b-it:d0c0442b34151c5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-03T13:20:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1336.2633420492373,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.24500604167221,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-08-23T00:03:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.769380358261,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.8828822319936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-23T04:48:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.0794653970897,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.659461887948076,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 129,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 223,
      "max_score": null,
      "measured_at": "2026-08-22T19:42:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1280.086612399988,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.20187949344528,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 96
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:stepfun-step-3-7-flash:efafeb77b13aa96b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1286.5573647608894,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.9662488064309,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 31,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-05T02:42:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1289.8281165492485,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.775234501033314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 27.779077868707382,
      "unilateral_faults": null,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 74,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 95,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1260.2930330590852,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.21820378332707,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:inclusionai-ling-3-0-flash:6f99584b1bad82dc",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 25,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 135,
      "max_score": null,
      "measured_at": "2026-08-22T10:20:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1258.6020053075358,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.146595980997496,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.132002100700243,
      "unilateral_faults": null,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:nex-agi-nex-n2-pro:bfccd9446404db2c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-05T05:35:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1208.098508332924,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.29442357821482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-08-21T05:34:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1169.8992765543176,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.952752097603227,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 118,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 256,
      "max_score": null,
      "measured_at": "2026-08-23T00:03:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1157.4214480942765,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.76063329257293,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 79,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1883.547354485846,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 87.44155540902236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.419488455005332,
      "unilateral_faults": 0,
      "wins": 131
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-19T21:56:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1852.419205680889,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 84.56963011340204,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-05T02:27:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1805.412687918018,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 79.13676897206143,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-05T03:27:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1752.1617029482936,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 73.85605709393225,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T04:28:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1736.9661240517378,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.16061484597145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1717.0113447747601,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 70.51569207279049,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-05T01:31:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1702.8026322218134,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.84294122769712,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-08-05T02:27:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.3057314183425,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 64.8042465369897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-05T04:28:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.6647109838646,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 62.86088508787239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T05:17:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.3758195563273,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 62.569827155594346,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1584.771978631998,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.923104326447486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 70,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 96,
      "max_score": null,
      "measured_at": "2026-08-19T21:21:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 186,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.6069463139568,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.278112032107714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 119,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-08-22T19:47:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1567.0074698000692,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.64840056444847,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 1.042462425705284,
      "unilateral_faults": 0,
      "wins": 155
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-31T01:11:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.6193285283734,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.449200646157834,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-22T23:00:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.6587539842521,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.37264260162897,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1513.4758066512193,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.52329772108889,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.1505201787807,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.25998902213876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:nex-agi-nex-n2-pro:bfccd9446404db2c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-05T00:37:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.7368378046194,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.573486962202864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-05T03:34:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.3408603140847,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.83708028920805,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-22T15:50:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.2649898641687,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.504378523447755,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:2437b68c7c28667e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.9631011121937,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.03435356364199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 82,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 87,
      "max_score": null,
      "measured_at": "2026-08-04T23:37:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.2767735661741,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.53573291311461,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.614857365683216,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-03T15:18:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.504688670992,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.06936748228342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:inclusionai-ling-3-0-flash:6f99584b1bad82dc",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 206,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 366,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.2579842748223,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.039137688291845,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.992023749735065,
      "unilateral_faults": null,
      "wins": 160
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.5715457857082,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.8825963105233,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 20.686604258614558,
      "unilateral_faults": null,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemma-4-31b-it:d0c0442b34151c5a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-04T21:46:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.8604269782086,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.44657904798219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 96,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.3017135371133,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.923736548942394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.19101199758159,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.9786554793234,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.80079783582027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-22T06:50:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.0796217693523,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.00669500599334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 80,
      "max_score": null,
      "measured_at": "2026-07-31T03:07:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.295129846862,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.67741814723562,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.4711027318722,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.06804835684683,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.4789526855327,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.04689513213039,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 310,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 187,
      "max_score": null,
      "measured_at": "2026-08-23T10:07:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 310,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.2444957042999,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.23200509894748,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.1870209205915,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.15058763153171,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 107,
      "max_score": null,
      "measured_at": "2026-08-19T21:43:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1306.4568832534878,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.874737705095153,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-08-05T01:38:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1264.6371016053838,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.563915845571497,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 113,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1169.155353986958,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 14.602532202469558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:7859dde46c855271",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-08-04T23:43:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1160.2853336204507,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 12.425400361217248,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 135,
      "max_score": null,
      "measured_at": "2026-08-22T12:49:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 152,
      "rating_method": "sequential_elo",
      "raw_elo": 1092.4543600337247,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 6.641760874582254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1045.4789996487496,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 0.5096881306947669,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:x-ai-grok-4-5:9ade9c53df23b855",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-04T23:52:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1917.0549563802338,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 87.21199208118166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 80
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-opus-4-5:6145092901d96725",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-21T15:41:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1878.7242423201383,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium effort + 16,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium effort + 16,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 84.27791783076424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 140
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-opus-5:f836f90d8fb9ff19",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 91,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-05T05:26:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 182,
      "rating_method": "sequential_elo",
      "raw_elo": 1888.389709769168,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 84.14512161801667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.380913286308589,
      "unilateral_faults": 0,
      "wins": 156
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-fable-5:0d812a1d2c768408",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T04:34:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1794.8063548988707,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 74.18412112706072,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-6-flash:157bc5e3bd81a2f8",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1755.9191643788624,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 71.15699062079223,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:meta-muse-spark-1-2:996fe7c6ac30c7b0",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-21T18:11:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1696.938698515543,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 64.10305893387694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:moonshotai-kimi-k2-7-code:d430d8b81bf58172",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-03T11:19:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K2.7 Code",
      "model_slug": "moonshotai-kimi-k2-7-code",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1688.6711614594897,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k2.7-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.086489595554106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-sol:60281ce94ea88014",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.2299897743615,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.42825918291155,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-5:d75099c830e67381",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-02T22:46:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.390503669571,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.44347013105038,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-8-max:2315ff339b0c18d0",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-22T18:02:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1632.7448564416845,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.180067856085,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4-nano:33b97f3221951ed8",
      "capped_draws": 46,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 81,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-08-04T20:41:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1574.610446657007,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.13298974653004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 10.807372224754609,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 103,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4:91029345b4b373cd",
      "capped_draws": 53,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 53,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 103,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.0480758610206,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.49874489923657,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.279033784546012,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:o3:48e82ad54f426340",
      "capped_draws": 57,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-03T12:36:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.633977758998,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.99479029724878,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-terra:02f87be2a684b52a",
      "capped_draws": 48,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 48,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-05T03:28:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.1846041302629,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.74024783687207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-1-flash-lite:036cd5692d58f681",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.4974729461187,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.003099708266724,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:stealth-ox-alpha:03024ebf053d776c",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-23T14:11:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.424913229797,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.82700014011026,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-4-mini:84a1457658ce88c0",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-05T05:18:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.4598339312142,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.437872589956235,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-7-max:a50a8f268d5fb73a",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1427.2167537575,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.278925993132454,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:openai-gpt-oss-120b:da344fed618b3552",
      "capped_draws": 79,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:33:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.316763828664,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.18482189543753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:qwen-qwen3-7-plus:ea7926e26c1cc685",
      "capped_draws": 88,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 88,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T00:36:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.7461884339903,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.251405081567306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:minimax-minimax-m3:f94aa3c94cf69a34",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-05T01:31:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.7357176254268,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.21198399845459,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:nvidia-nemotron-3-ultra-550b-a55b:7859dde46c855271",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1417.7124167603577,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.04456627680913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:x-ai-grok-build-0-1:40e9bde1c6eafc11",
      "capped_draws": 81,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-build-0.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-04T23:07:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok Build 0.1",
      "model_slug": "x-ai-grok-build-0-1",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.9235515651562,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-build-0.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.62877770432017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:z-ai-glm-5-2:f8720fd50b424f28",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.9737693629816,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.627097160286695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-opus-4-8:7ef4979f6b3e9a70",
      "capped_draws": 75,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 75,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-04T23:29:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.511822163267,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.12565451149703,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:deepseek-deepseek-v4-flash:ca5e50927e9f8fc5",
      "capped_draws": 128,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 72,
      "draws": 128,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-07-31T03:35:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.5458902114271,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.54211074905695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:thinkingmachines-inkling-small:76482ff3d2fed50c",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-21T20:21:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.0959389047707,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.26674941355504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 184,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:moonshotai-kimi-k3:b25ef0843c2d972a",
      "capped_draws": 129,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 71,
      "draws": 129,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 184,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.978890026653,
      "reasoning_bracket": "balanced",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.270736967846446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:xiaomi-mimo-v2-5:f4cab288f8f1ec59",
      "capped_draws": 84,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 81,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-08-04T21:46:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.024127139457,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.594776874486953,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.898185915470545,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:xiaomi-mimo-v2-5-pro:2437b68c7c28667e",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-04T08:41:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.997724777921,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.43712263783562,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:claude-sonnet-5:765bc291b12a711e",
      "capped_draws": 52,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-21T15:02:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1384.1626713883547,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.349808387715242,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 305,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:meituan-longcat-2-0:26225fa06d2cccd9",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 117,
      "draws": 95,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 150,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 305,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.878037318353,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.011204993640277,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 332,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:poolside-laguna-s-2-1:df6bf1faab8cda70",
      "capped_draws": 224,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 126,
      "draws": 224,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-08-22T11:41:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 332,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.6049159769764,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Enabled",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.56068444949395,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5:4164dfc523f2863c",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:19:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1362.3112742107332,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.79276252693172,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-5-flash:602942e58ad38e29",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-03T02:54:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1360.7075347534644,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.62507347872291,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": null,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:cohere-north-mini-code:b73629af9e588e3b",
      "capped_draws": null,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 30,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "balanced",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-05T04:28:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.9716806578233,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Balanced track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Balanced",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "balanced"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.8658776184786,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 33.16054548991772,
      "unilateral_faults": null,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:google-gemini-3-5-flash-lite:ada8852a63812f17",
      "capped_draws": 209,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 209,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.1974425120047,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.219997210607445,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 153,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:thinkingmachines-inkling:3ab0a3aec8e194a6",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 92,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-21T18:11:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 153,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.0261862668438,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.64774117358596,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:gpt-5-6-luna:56b3e8082c8d4caf",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "medium",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.6533845849854,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Medium",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "medium",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openai",
        "provider_setting_label": "Medium",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Medium",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "medium"
      },
      "reasoning_setting": "medium",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.07186922308482,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:balanced:nex-agi-nex-n2-pro:bfccd9446404db2c",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "enabled",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-08-05T02:33:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1217.152242285979,
      "reasoning_bracket": "balanced",
      "reasoning_level": "Reasoning enabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "balanced",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "enabled",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/balanced"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning enabled",
        "reasoning_bracket": "balanced",
        "reasoning_bucket": "balanced",
        "reasoning_bucket_label": "Reasoning enabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "enabled"
      },
      "reasoning_setting": "enabled",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 13.67320578769338,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/balanced",
      "track_name": "Balanced filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1286,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 107,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 2,
        "max": 0.5221625,
        "mean": 0.2856328125,
        "median": 0.2536225,
        "min": 0.2178175,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 4.570125
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 70.79162335985623,
      "contributing_entrants": null,
      "distinct_rated_opponents": 44,
      "draws": 261,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 14,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-21T15:53:02Z",
      "losses": 215,
      "max_score": 90.96243393579934,
      "measured_at": null,
      "min_score": 51.301004509305145,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1285,
      "rating_method": "sequential_elo",
      "raw_elo": 1745.7190424540813,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 68.46740765742071,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 809
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 698,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 17,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.15394249999999998,
        "mean": 0.12786562499999998,
        "median": 0.13029000000000002,
        "min": 0.10071375,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.0229249999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 55.76248795572135,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 161,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T03:03:24Z",
      "losses": 172,
      "max_score": 78.74292256811869,
      "measured_at": null,
      "min_score": 27.127464596852075,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 698,
      "rating_method": "sequential_elo",
      "raw_elo": 1613.2432870557532,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 55.76248795572135,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 365
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1338,
      "canonical_public_row_identity": "publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 133,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "max": 0.1077678,
        "mean": 0.076003275,
        "median": 0.070269,
        "min": 0.0550338,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.6080262000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 53.41264234414682,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 396,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T04:48:24Z",
      "losses": 361,
      "max_score": 98.88106339111127,
      "measured_at": null,
      "min_score": 22.928875872336782,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 1.0,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1338,
      "rating_method": "sequential_elo",
      "raw_elo": 1579.9446710142442,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 53.41264234414682,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 581
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 678,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 83,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.144235,
        "mean": 0.12174125,
        "median": 0.121475,
        "min": 0.09594,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.97393
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 48.974391609272004,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 237,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:02:30Z",
      "losses": 187,
      "max_score": 70.0969711174775,
      "measured_at": null,
      "min_score": 26.56425672722357,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 678,
      "rating_method": "sequential_elo",
      "raw_elo": 1545.2756966245358,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 48.974391609272004,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 254
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 554,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "capped_draws": 20,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.190125,
        "mean": 0.15785312499999998,
        "median": 0.15388000000000002,
        "min": 0.131495,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.2628250000000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 49.15100352600054,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 147,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:47:33Z",
      "losses": 161,
      "max_score": 73.81276758326433,
      "measured_at": null,
      "min_score": 19.14734246410184,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 554,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.4818809927506,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 47.53728810652374,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 246
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1225,
      "canonical_public_row_identity": "publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 126,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "max": 0.0992248,
        "mean": 0.07433795,
        "median": 0.0774068,
        "min": 0.0424244,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.5947036
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.42173740142161,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 383,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T13:45:16Z",
      "losses": 372,
      "max_score": 85.5368320379681,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1225,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.1992204536268,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 46.42173740142161,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 470
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 720,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 64,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.179715,
        "mean": 0.09608781250000001,
        "median": 0.08063500000000001,
        "min": 0.0656625,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.7687025000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.47321666269807,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 216,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T07:54:09Z",
      "losses": 240,
      "max_score": 75.15416974608023,
      "measured_at": null,
      "min_score": 17.905822221963863,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 720,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.924260921312,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 43.47321666269807,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 264
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 998,
      "canonical_public_row_identity": "publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 85,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 24
        },
        "evidence_basis": "Provider-reported",
        "max": 0.047757869999999994,
        "mean": 0.022448211274999998,
        "median": 0.017169796,
        "min": 0.0106770175,
        "recorded_attempt_count": 24,
        "run_count": 16,
        "total": 0.35917138039999996
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 42.77028062419599,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 327,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T20:23:06Z",
      "losses": 346,
      "max_score": 59.57776973557898,
      "measured_at": null,
      "min_score": 18.537461190466654,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 998,
      "rating_method": "sequential_elo",
      "raw_elo": 1504.3430410272745,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.77028062419599,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 325
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 574,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 94,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.03912625,
        "mean": 0.022799843750000003,
        "median": 0.021642500000000002,
        "min": 0.015285,
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.18239875
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.48832517883199,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 190,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:33:39Z",
      "losses": 194,
      "max_score": 68.87219421844685,
      "measured_at": null,
      "min_score": 24.982247392476896,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": 0.875,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 568,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.5470816100574,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.06052562492911,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 184
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 662,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 101,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.1192425,
        "mean": 0.0683559375,
        "median": 0.06152125,
        "min": 0.0542775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 9,
        "token_priced_attempt_count": 10,
        "total": 0.6063375
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 43.16044727061799,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 265,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.7777777777777778,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:05:30Z",
      "losses": 206,
      "max_score": 55.20092432661375,
      "measured_at": null,
      "min_score": 28.236124905450517,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 660,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.4124877399488,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.1111111111111111,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 41.90808402618568,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 189
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 652,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 79,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.09459400000000001,
        "mean": 0.0571955,
        "median": 0.043012,
        "min": 0.032534,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 0.457564
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.47586576190677,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 228,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:31Z",
      "losses": 224,
      "max_score": 63.331047607164344,
      "measured_at": null,
      "min_score": 18.508036486618778,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 651,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.0273047777948,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 41.47586576190677,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 199
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 675,
      "canonical_public_row_identity": "publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 55,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.07847,
        "mean": 0.06167125,
        "median": 0.061313,
        "min": 0.051588,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.49337
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.22590804755895,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 190,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:40:55Z",
      "losses": 272,
      "max_score": 57.13966476484938,
      "measured_at": null,
      "min_score": 18.901290276570073,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 675,
      "rating_method": "sequential_elo",
      "raw_elo": 1471.8812004216354,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 41.22590804755895,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 213
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 594,
      "canonical_public_row_identity": "publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 117,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 12
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.029078938,
        "mean": 0.015562441375000001,
        "median": 0.013116718500000001,
        "min": 0.005612805,
        "recorded_attempt_count": 12,
        "run_count": 8,
        "total": 0.12449953100000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 42.13826236852083,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 207,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:18:01Z",
      "losses": 187,
      "max_score": 66.56206174162008,
      "measured_at": null,
      "min_score": 22.057846645260756,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 594,
      "rating_method": "sequential_elo",
      "raw_elo": 1491.5101689138505,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 40.75478779311221,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 200
    },
    {
      "admitted_plugins": 15,
      "attempted_matches": 2243,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 310,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 34
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.0222516,
        "mean": 0.01697319375,
        "median": 0.015739925000000002,
        "min": 0.012759,
        "recorded_attempt_count": 34,
        "run_count": 16,
        "total": 0.2715711
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 41.236974524375064,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 730,
      "eligibility_flag": true,
      "entry_count": 15,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 9,
      "first_pass_rate": 0.5625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:51:52Z",
      "losses": 845,
      "max_score": 73.02102977984342,
      "measured_at": null,
      "min_score": 10.571254109747576,
      "model_code_failure_rate": 0.0625,
      "model_code_failures": 1,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.9375,
      "provider": "Google",
      "provider_key": "google",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2237,
      "rating_method": "sequential_elo",
      "raw_elo": 1458.0623223001046,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 40.576969969102905,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 662
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 688,
      "canonical_public_row_identity": "publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 42,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 9
        },
        "evidence_basis": "Provider-reported",
        "max": 0.03564825,
        "mean": 0.0239263125,
        "median": 0.02294625,
        "min": 0.01939525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "recorded_attempt_count": 9,
        "run_count": 8,
        "total": 0.1914105
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.239933673861195,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 163,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:38:06Z",
      "losses": 299,
      "max_score": 59.44710258784996,
      "measured_at": null,
      "min_score": 16.944819699504418,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 688,
      "rating_method": "sequential_elo",
      "raw_elo": 1462.5633851043924,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 40.239933673861195,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 226
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 612,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 167,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.156555,
        "mean": 0.1422525,
        "median": 0.14850249999999998,
        "min": 0.12078,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 1.13802
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.54520036195957,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 318,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:23:57Z",
      "losses": 157,
      "max_score": 53.951577978721,
      "measured_at": null,
      "min_score": 19.58339791797017,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 612,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.270127769893,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 39.214028863594145,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 137
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1217,
      "canonical_public_row_identity": "publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 237,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 33
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.00407402,
        "mean": 0.0029986699999999997,
        "median": 0.00314426,
        "min": 0.0012446800000000002,
        "recorded_attempt_count": 33,
        "run_count": 14,
        "total": 0.04176386
      },
      "codegen_evaluated_cells": 14,
      "conditional_success_score": 39.52658657172093,
      "contributing_entrants": null,
      "distinct_rated_opponents": 46,
      "draws": 423,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "infra_failures_excluded": 2,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T23:51:52Z",
      "losses": 408,
      "max_score": 57.87934682152756,
      "measured_at": null,
      "min_score": 19.31198981966688,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 2,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Other",
      "provider_key": "other",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1209,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.4068445555506,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 5,
      "repaired_rate": 0.35714285714285715,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 38.03230207729145,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 378
    },
    {
      "admitted_plugins": 16,
      "attempted_matches": 2451,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 307,
      "codegen_cost_usd": {
        "admitted_cell_count": 16,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 29
        },
        "evidence_basis": "Provider-reported",
        "max": 0.07826175,
        "mean": 0.05584070625,
        "median": 0.0541695,
        "min": 0.0411735,
        "recorded_attempt_count": 29,
        "run_count": 16,
        "total": 0.8934513000000002
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 37.771112166458195,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 861,
      "eligibility_flag": true,
      "entry_count": 16,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 12,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T13:45:16Z",
      "losses": 916,
      "max_score": 55.01429727686298,
      "measured_at": null,
      "min_score": 17.43890191914832,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 1.0,
      "provider": "Google",
      "provider_key": "google",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2447,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.2795842311334,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 37.771112166458195,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 670
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 524,
      "canonical_public_row_identity": "publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 26,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.09803328,
        "mean": 0.0253809975,
        "median": 0.00943521,
        "min": 0.00639384,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.20304798000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 40.388823983582036,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 119,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:33:21Z",
      "losses": 198,
      "max_score": 52.04366523994301,
      "measured_at": null,
      "min_score": 16.460871449147128,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": 0.75,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 524,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.0405300009095,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 37.58603585254086,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 207
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 478,
      "canonical_public_row_identity": "publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 97,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.001632522,
        "mean": 0.00126739675,
        "median": 0.001232095,
        "min": 0.00090937,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.010139173999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.95580492735129,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 212,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:08:37Z",
      "losses": 125,
      "max_score": 72.88756496655336,
      "measured_at": null,
      "min_score": 13.368124963630589,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": 0.75,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 472,
      "rating_method": "sequential_elo",
      "raw_elo": 1489.0265940507213,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 37.18306621472872,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 135
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1020,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 137,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 27
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.01311555,
        "mean": 0.009215359375,
        "median": 0.009537575,
        "min": 0.004854125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 27
        },
        "run_count": 16,
        "token_priced_attempt_count": 27,
        "total": 0.14744575000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 38.748743740948335,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 307,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-07"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.3125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:31Z",
      "losses": 386,
      "max_score": 56.113615016738166,
      "measured_at": null,
      "min_score": 19.627918979635304,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": 0.75,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1014,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.9027140773464,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 36.05976920942859,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 321
    },
    {
      "admitted_plugins": 11,
      "attempted_matches": 1328,
      "canonical_public_row_identity": "publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 181,
      "codegen_cost_usd": {
        "admitted_cell_count": 17,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 37
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.005169185000000001,
        "mean": 0.002871050658333333,
        "median": 0.0023354879666666667,
        "min": 0.00169122,
        "recorded_attempt_count": 37,
        "run_count": 24,
        "total": 0.06890521579999999
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 38.376735596133805,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 370,
      "eligibility_flag": true,
      "entry_count": 17,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.4375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:45Z",
      "losses": 512,
      "max_score": 50.80751645753057,
      "measured_at": null,
      "min_score": 19.75239474357151,
      "model_code_failure_rate": 0.3125,
      "model_code_failures": 5,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.6875,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1326,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.4455573260527,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.945093403078104,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 444
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 450,
      "canonical_public_row_identity": "publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "capped_draws": 84,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.13485595000000003,
        "mean": 0.031792056250000006,
        "median": 0.0158481,
        "min": 0.0111232,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.38919240000000005
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 36.85807193397447,
      "contributing_entrants": null,
      "distinct_rated_opponents": 36,
      "draws": 149,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-07"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.5555555555555556,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T03:28:04Z",
      "losses": 183,
      "max_score": 59.683472652436585,
      "measured_at": null,
      "min_score": 10.490412921476183,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 450,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.4077671585844,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.61357810936488,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 118
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1118,
      "canonical_public_row_identity": "publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 99,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 39
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.0721503,
        "mean": 0.03677837187500001,
        "median": 0.0324098875,
        "min": 0.01945095,
        "recorded_attempt_count": 39,
        "run_count": 16,
        "total": 0.58845395
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.58136186400597,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 338,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.4375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:23:15Z",
      "losses": 465,
      "max_score": 68.95924601863939,
      "measured_at": null,
      "min_score": 12.558196600852206,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.75,
      "provider": "Other",
      "provider_key": "other",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1118,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.3474412764351,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.04279310321619,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 315
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1312,
      "canonical_public_row_identity": "publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 271,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 38
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.021206376000000002,
        "mean": 0.01337795025,
        "median": 0.01381146,
        "min": 0.006392298,
        "recorded_attempt_count": 38,
        "run_count": 16,
        "total": 0.214047204
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 35.0433047714104,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 471,
      "eligibility_flag": true,
      "entry_count": 14,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:24:42Z",
      "losses": 490,
      "max_score": 55.24795980739564,
      "measured_at": null,
      "min_score": 17.33176752068492,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": 0.875,
      "provider": "Other",
      "provider_key": "other",
      "rank": 25,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1308,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.959860969325,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 6,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 33.892770352939465,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 347
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 662,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 104,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.03021,
        "mean": 0.0183815625,
        "median": 0.015581250000000001,
        "min": 0.01245825,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 0.1470525
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.595878931104806,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 298,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:24:08Z",
      "losses": 240,
      "max_score": 43.819799277453555,
      "measured_at": null,
      "min_score": 7.108412173273799,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 26,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 658,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.6062193453638,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 30.595878931104806,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 120
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 572,
      "canonical_public_row_identity": "publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 80,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00408087,
        "mean": 0.0022664345375,
        "median": 0.0017928150000000001,
        "min": 0.0013289177,
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.018131476299999998
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 30.234451879974593,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 226,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:23:15Z",
      "losses": 224,
      "max_score": 44.17279269378332,
      "measured_at": null,
      "min_score": 19.782102062746848,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.875,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 27,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 572,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.7074437784765,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 29.24180070913258,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 122
    },
    {
      "admitted_plugins": 10,
      "attempted_matches": 1210,
      "canonical_public_row_identity": "publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 339,
      "codegen_cost_usd": {
        "admitted_cell_count": 10,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 40
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 6,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 40,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 28.744961396455825,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 607,
      "eligibility_flag": true,
      "entry_count": 10,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-07"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:41:59Z",
      "losses": 408,
      "max_score": 40.59443860612531,
      "measured_at": null,
      "min_score": 16.708450302583884,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 6,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": 0.625,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": 28,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1206,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.7257065197282,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 25.558286496840537,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 507,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "capped_draws": 25,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0154064,
        "mean": 0.00874386,
        "median": 0.0064215999999999995,
        "min": 0.00524064,
        "recorded_attempt_count": 13,
        "run_count": 9,
        "total": 0.08145696
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 27.93935400151837,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 160,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.4444444444444444,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:19:33Z",
      "losses": 235,
      "max_score": 48.468260024253375,
      "measured_at": null,
      "min_score": 3.600933227553536,
      "model_code_failure_rate": 0.3333333333333333,
      "model_code_failures": 3,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": 0.6666666666666666,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": 29,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 505,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.6872091475514,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 25.246056255336732,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 110
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 689,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 28,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0057713,
        "mean": 0.004598475,
        "median": 0.0045067,
        "min": 0.0040101,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.036787799999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 20.481562275645565,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 187,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:40:55Z",
      "losses": 414,
      "max_score": 37.05506647400019,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 30,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 689,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.7762312967425,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 20.481562275645565,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 88
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 346,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemini-3-1-flash-lite:483a08d2c98ab52c",
      "capped_draws": 24,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.00870475,
        "mean": 0.005883593750000001,
        "median": 0.006313125,
        "min": 0.003432,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.047068750000000006
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 18.361836436012375,
      "contributing_entrants": null,
      "distinct_rated_opponents": 35,
      "draws": 80,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T03:34:49Z",
      "losses": 200,
      "max_score": 41.31086220995625,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.625,
      "provider": "Google",
      "provider_key": "google",
      "rank": 31,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 346,
      "rating_method": "sequential_elo",
      "raw_elo": 1248.4031660913797,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 16.326237832331643,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 1094,
      "canonical_public_row_identity": "publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 126,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 13
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.0032939400000000004,
        "mean": 0.0016413085000000001,
        "median": 0.0014119655,
        "min": 0.00045831,
        "recorded_attempt_count": 13,
        "run_count": 8,
        "total": 0.013130468
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 15.021272069324533,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 230,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T13:45:04Z",
      "losses": 710,
      "max_score": 25.677590362951314,
      "measured_at": null,
      "min_score": 0.0,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 32,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1094,
      "rating_method": "sequential_elo",
      "raw_elo": 1198.9148599375305,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 14.528096821221972,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 154
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-row.v1:baseline:gpt-4-1-nano:e6370d2aaad0f23a",
      "capped_draws": 35,
      "codegen_cost_usd": {
        "admitted_cell_count": 1,
        "cell_count": 1,
        "cost_basis_counts": {
          "estimated": 1,
          "local_standard_estimate": 1
        },
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "max": 0.0023425,
        "mean": 0.0023425,
        "median": 0.0023425,
        "min": 0.0023425,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 1,
          "boardgame-list-prices-2026-08-08": 1
        },
        "recorded_attempt_count": 1,
        "run_count": 1,
        "token_priced_attempt_count": 1,
        "total": 0.0023425
      },
      "codegen_evaluated_cells": 1,
      "conditional_success_score": 39.72974279439747,
      "contributing_entrants": null,
      "distinct_rated_opponents": 25,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": 1,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1-nano",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 1,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-14T22:12:59Z",
      "losses": 67,
      "max_score": 39.72974279439747,
      "measured_at": null,
      "min_score": 39.72974279439747,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.5094730893666,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Reasoning field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 39.72974279439747,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 504,
      "canonical_public_row_identity": "publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "capped_draws": 33,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 10
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.1311545862,
        "mean": 0.02955606902857143,
        "median": 0.0063034062,
        "min": 0.0057139812,
        "recorded_attempt_count": 10,
        "run_count": 7,
        "total": 0.2068924832
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 40.66399209647054,
      "contributing_entrants": null,
      "distinct_rated_opponents": 36,
      "draws": 122,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5714285714285714,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:19:05Z",
      "losses": 183,
      "max_score": 52.982816468950794,
      "measured_at": null,
      "min_score": 25.444968645038077,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 1,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 504,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.5531363843731,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.2857142857142857,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 39.12670850733229,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 16,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "evidence_basis": "Provider-reported",
        "max": 0.173358,
        "mean": 0.1197105,
        "median": 0.119348,
        "min": 0.066054,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "total": 0.957684
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.749029621979645,
      "contributing_entrants": null,
      "distinct_rated_opponents": 14,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T02:23:52Z",
      "losses": 45,
      "max_score": 65.33787445900813,
      "measured_at": null,
      "min_score": 7.529917385447114,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": 1.0,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.251651276839,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.749029621979645,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 141,
      "canonical_public_row_identity": "publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.014791950000000002,
        "mean": 0.007616140625,
        "median": 0.005694875,
        "min": 0.00430875,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.07206399999999999
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 32.851444464888665,
      "contributing_entrants": null,
      "distinct_rated_opponents": 17,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.5555555555555556,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:13:39Z",
      "losses": 61,
      "max_score": 42.18481948599077,
      "measured_at": null,
      "min_score": 15.033187607000485,
      "model_code_failure_rate": 0.1111111111111111,
      "model_code_failures": 1,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": 0.8888888888888888,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 141,
      "rating_method": "sequential_elo",
      "raw_elo": 1442.932625654153,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 3,
      "repaired_rate": 0.3333333333333333,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.898211952807085,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 576,
      "canonical_public_row_identity": "publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 93,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 36
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 9,
        "max": 0.215758025,
        "mean": 0.16162675,
        "median": 0.1594081875,
        "min": 0.098579625,
        "recorded_attempt_count": 36,
        "run_count": 16,
        "total": 2.5860279999999998
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 38.57817288064592,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 261,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:41:06Z",
      "losses": 174,
      "max_score": 63.528190114310334,
      "measured_at": null,
      "min_score": 16.61661173350593,
      "model_code_failure_rate": 0.5625,
      "model_code_failures": 9,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": 0.4375,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 576,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.545103745422,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.375175900391902,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 141
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 560,
      "canonical_public_row_identity": "publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "capped_draws": 105,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 7,
        "cost_basis_counts": {
          "provider_reported": 8
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 1,
        "max": 0.00391754,
        "mean": 0.0023617857142857143,
        "median": 0.00186618,
        "min": 0.00144036,
        "recorded_attempt_count": 8,
        "run_count": 7,
        "total": 0.0165325
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 32.366653836465424,
      "contributing_entrants": null,
      "distinct_rated_opponents": 40,
      "draws": 168,
      "eligibility_flag": false,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.7142857142857143,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:48:11Z",
      "losses": 235,
      "max_score": 44.033324039853156,
      "measured_at": null,
      "min_score": 18.568992620174647,
      "model_code_failure_rate": 0.14285714285714285,
      "model_code_failures": 1,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": 0.8571428571428571,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 558,
      "rating_method": "sequential_elo",
      "raw_elo": 1349.5759456811304,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 1,
      "repaired_rate": 0.14285714285714285,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.14304731844145,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 155
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 634,
      "canonical_public_row_identity": "publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 99,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.03772852,
        "mean": 0.024905897500000003,
        "median": 0.026095300000000002,
        "min": 0.00984735,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.19924718000000002
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.916379646070055,
      "contributing_entrants": null,
      "distinct_rated_opponents": 37,
      "draws": 110,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T10:07:05Z",
      "losses": 321,
      "max_score": 52.921447482930446,
      "measured_at": null,
      "min_score": 22.799140452263753,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.5,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 630,
      "rating_method": "sequential_elo",
      "raw_elo": 1378.0519781417672,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.0428513085255,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 199
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 396,
      "canonical_public_row_identity": "publication-row.v1:baseline:mistralai-mistral-medium-3-5:34da7964c6511272",
      "capped_draws": 96,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.06200699999999999,
        "mean": 0.042994687499999996,
        "median": 0.0423105,
        "min": 0.0223935,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.34395749999999997
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 36.54412660468169,
      "contributing_entrants": null,
      "distinct_rated_opponents": 36,
      "draws": 104,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-07"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:49:34Z",
      "losses": 155,
      "max_score": 40.86555647776021,
      "measured_at": null,
      "min_score": 30.076430145642476,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": 0.5,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 376,
      "rating_method": "sequential_elo",
      "raw_elo": 1383.894700456406,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 30.729825060454733,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 20,
      "wins": 117
    },
    {
      "admitted_plugins": 28,
      "attempted_matches": 326,
      "canonical_public_row_identity": "publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 15,
      "codegen_cost_usd": {
        "admitted_cell_count": 28,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 42
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 42,
        "run_count": 30,
        "total": 0.0
      },
      "codegen_evaluated_cells": 30,
      "conditional_success_score": 31.110992060585442,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": 22,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-08"
      ],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.6333333333333333,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T15:12:59Z",
      "losses": 155,
      "max_score": 45.08609625332008,
      "measured_at": null,
      "min_score": 3.8514807674763087,
      "model_code_failure_rate": 0.06666666666666667,
      "model_code_failures": 2,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": 0.9333333333333333,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 321,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.0019137585693,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 9,
      "repaired_rate": 0.3,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 30.57898417462382,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 83
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 639,
      "canonical_public_row_identity": "publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 147,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 8,
          "local_standard_estimate": 13
        },
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 4,
        "max": 0.17217,
        "mean": 0.11039474999999999,
        "median": 0.10846,
        "min": 0.07562,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 13,
          "boardgame-list-prices-2026-08-08": 8
        },
        "recorded_attempt_count": 8,
        "run_count": 8,
        "token_priced_attempt_count": 13,
        "total": 0.8831580000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 27.169386199575268,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 172,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:51:52Z",
      "losses": 351,
      "max_score": 53.99459166857962,
      "measured_at": null,
      "min_score": 2.8219078055756306,
      "model_code_failure_rate": 0.5,
      "model_code_failures": 4,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.5,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 639,
      "rating_method": "sequential_elo",
      "raw_elo": 1285.2133752396462,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 22.846639459866584,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 496,
      "canonical_public_row_identity": "publication-row.v1:baseline:cohere-north-mini-code:3e6a1897cfdaa330",
      "capped_draws": 182,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 30
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 11,
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 30,
        "run_count": 16,
        "total": 0.0
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 27.306622154385593,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 182,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-08"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.1875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:09:16Z",
      "losses": 232,
      "max_score": 33.85875457644092,
      "measured_at": null,
      "min_score": 23.179971665322682,
      "model_code_failure_rate": 0.6875,
      "model_code_failures": 11,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": 0.3125,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 492,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.214856005476,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": 2,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 20.41646207891444,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-19T22:28:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1827.927379066235,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 78.74292256811869,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-19T23:52:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1772.7929800733582,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 73.18339250918713,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-05T05:08:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1773.8960199591977,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.88756496655336,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 204,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 92,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-05T05:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 203,
      "rating_method": "sequential_elo",
      "raw_elo": 1702.542944257067,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 66.07679415920771,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.658091940411904,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 91,
      "rating_method": "sequential_elo",
      "raw_elo": 1678.161582569883,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.331047607164344,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.378603514268699,
      "unilateral_faults": 1,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-07-31T02:19:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.4221322011101,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.386461607802104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 182,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 86,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-05T05:01:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.1217179945165,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.113615016738166,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.340523799551441,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-07-31T01:07:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.7687032819815,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.548619261546875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-08-05T03:05:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1589.2703740811967,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.857347305850986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 21,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.9122301422362,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.04366523994301,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-07-31T03:24:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.6015315816996,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.92333504583319,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 84,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.1824746630828,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.52153198061598,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 210,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 50,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 101,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 210,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.667219495499,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.51241566794083,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.854879649062207,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 278,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 60,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 138,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-08-05T01:58:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 278,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.2198636800767,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.477225211933856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.221152076234401,
      "unilateral_faults": 0,
      "wins": 104
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 191,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 130,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 130,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-20T02:03:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 191,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.1217619645342,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.250941248501725,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 197,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 126,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 75,
      "draws": 126,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-23T09:56:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 197,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.9335994737546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.760117376536684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-05T03:13:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.7710394884484,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.033324039853156,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 44,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-05T04:18:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 116,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.983885430028,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.640363221816266,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.4750163521024238,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 87,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-23T12:40:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 87,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.2271709641848,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.183715862077705,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.550179088902606,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 116,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:mistralai-mistral-medium-3-5:34da7964c6511272",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:10:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.7788681959753,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.86555647776021,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 20,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 71,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.1253265344149,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.3121483931683,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-4-1-nano:e6370d2aaad0f23a",
      "capped_draws": 35,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1-nano",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-14T22:12:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1 Nano",
      "model_slug": "gpt-4-1-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.5094730893666,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Reasoning field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning field omitted",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.72974279439747,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 60
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-22T09:27:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.182936178097,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.68437234670113,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 294,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 95,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "draws": 95,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 294,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.6441048464835,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.99825914849188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "capped_draws": 29,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:19:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1418.7059748335482,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.856998866883636,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 342,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 130,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 157,
      "max_score": null,
      "measured_at": "2026-08-22T14:46:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 342,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.6662439845072,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.62677721692003,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 111
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 78,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 109,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 88,
      "max_score": null,
      "measured_at": "2026-08-05T05:02:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1386.391363495254,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.634762539218215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 2.706222621085206,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 38,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 38,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-08-05T05:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.9183970053725,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.44482183373839,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-23T12:17:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.826841528916,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.220512032278116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 37,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 37,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1376.434958978076,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.11260422145595,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 28,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 74,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 71,
      "max_score": null,
      "measured_at": "2026-07-31T03:20:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.590696843264,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.68527547982116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.046738977996931,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-04T23:49:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1330.725824672585,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.47909111397539,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-22T07:23:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.2484890428086,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.4679471098268,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:cohere-north-mini-code:3e6a1897cfdaa330",
      "capped_draws": 96,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 96,
      "draws": 96,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 89,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1287.6381095392642,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.179971665322682,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.667409425864287,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 74,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 126,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 183,
      "max_score": null,
      "measured_at": "2026-08-22T16:31:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1276.0173148882393,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.875190223871893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 89,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-23T12:40:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 89,
      "rating_method": "sequential_elo",
      "raw_elo": 1239.5383535693904,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.93516275734703,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.954627669472988,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 66,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 108,
      "max_score": null,
      "measured_at": "2026-08-22T09:27:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1226.334134979911,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.729065008395047,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 222,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 79,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 105,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 122,
      "max_score": null,
      "measured_at": "2026-08-05T05:09:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 222,
      "rating_method": "sequential_elo",
      "raw_elo": 1183.164429430121,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 12.558196600852206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.4969716034024056,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:google-gemini-3-1-flash-lite:483a08d2c98ab52c",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-07-31T03:26:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1168.6771765022436,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 10.192924369283574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 42,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 111,
      "max_score": null,
      "measured_at": "2026-08-20T02:24:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1082.9163024850677,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 2.8219078055756306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 75,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.9382682376422,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.97608367109741,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.60765757439077,
      "unilateral_faults": 0,
      "wins": 81
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 77,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-05T01:51:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.26315875289,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.236124905450517,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 121,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 107,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-23T03:23:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 121,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.1866099898193,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.69898854487774,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.5178730212592662,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-23T03:03:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.8831773296815,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.127464596852075,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-04T21:44:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.3332105179659,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.56425672722357,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-03T08:48:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.3456741149573,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.444968645038077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-04T20:03:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.9557794402522,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.982247392476896,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.2026519480598,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.312887404123998,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 148,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 130,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-19T23:37:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.3717066027084,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.928875872336782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 70,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-03T15:08:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1477.703775598533,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.057846645260756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:google-gemini-3-1-flash-lite:483a08d2c98ab52c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.2648473381566,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.497354945210386,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 84,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-05T02:59:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.566214509699,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.8256604365787,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 71,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-04T22:55:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.7375666323005,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.5446273273821,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.498417326438,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.821595384418693,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-05T00:29:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.3214890914899,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.782102062746848,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 28,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-07-31T02:24:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.3532370944224,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.75239474357151,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 248,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "draws": 226,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-22T08:45:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 248,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.9746151933264,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.712695556979902,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.975653602088653,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 77,
      "draws": 139,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.1081705185377,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.627918979635304,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.867341638060083,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-04T23:05:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.431303811449,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.58339791797017,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.0127959450965,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.31198981966688,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-05T02:59:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.1326032111256,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.14734246410184,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 85,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:26:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.934365357052,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.00038445855571,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.030300912858,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.901290276570073,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 57,
      "draws": 108,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-07-31T03:32:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.457526624261,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.537461190466654,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.910536671832062,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-22T07:54:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1460.9158431127426,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.905822221963863,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 246,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 91,
      "draws": 223,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-23T03:03:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.93655147432,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.43890191914832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.1611854626755758,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-19T21:57:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.9484790906874,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.944819699504418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 100,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-05T04:27:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.0482654162681,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.708450302583884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-05T04:32:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.9080120948634,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.61661173350593,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-05T04:33:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.2399661529485,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.460871449147128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1492.996408990712,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 15.033187607000485,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-20T02:43:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.2519536138268,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 14.67781433099459,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-31T02:27:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1444.9854646078195,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 13.368124963630589,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-22T08:45:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.8967197535371,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 7.529917385447114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 28,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.4161473966744,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 3.8514807674763087,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 73,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1586.1626741002503,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.81837924586282,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.377800258513929,
      "unilateral_faults": 0,
      "wins": 73
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.0346949443713,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.66426066452565,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-15T02:26:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.1523284131163,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.13966476484938,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.5926549807855,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 54.16096619535128,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-23T02:31:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1542.3820976110903,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.28442509273992,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-22T20:29:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1527.6522566987526,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.72856933942535,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.6746024305037,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.97927682744617,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 302,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 120,
      "draws": 98,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.994876963442,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.88685308179679,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 123
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.0178075202837,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.047889752679794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.9851115234762,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.4984550891471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1512.1972496241688,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.28468874615239,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.213976730923585,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-03T13:39:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.0571494972528,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.6580131540409,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:55:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.233407603528,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.12212623530856,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.899175382564,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.14726180448418,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-05T04:03:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.862249672601,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.819799277453555,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-22T11:01:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1518.820909745894,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.18481948599077,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 46,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-31T01:34:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.803408628788,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.12992846790356,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 29.23208533928221,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-03T15:07:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1466.1792879779643,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.969815876809534,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-05T03:54:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.8196949799096,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.43722567444062,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 35,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:57Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.9820939819956,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.34825846139262,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-05T02:49:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.812696623928,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.12729304970078,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 231,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 100,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 76,
      "max_score": null,
      "measured_at": "2026-08-22T23:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 231,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.945798874046,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.88354454110426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.902777777777777,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-03T04:31:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 56,
      "rating_method": "sequential_elo",
      "raw_elo": 1445.7895878905797,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.09206930228779,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 22.47661785325219,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T05:23:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.8471904592118,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.08306137270303,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 67,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.9868138511533,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.87102615666334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.213976730923585,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 23,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-04T22:38:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1410.904948282172,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.740913466707504,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 40,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-07-31T02:59:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 40,
      "rating_method": "sequential_elo",
      "raw_elo": 1414.0125908179525,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.268010627958816,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 34.33688094430304,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 12,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-23T15:12:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 23,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.2308212149396,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.219076953501776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 97.46252452815364,
      "unilateral_faults": 1,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 68,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.6716512399985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.68470258883002,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.29009959559265,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-21T11:43:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1370.3181825628085,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.125725179167283,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 13,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-22T20:29:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 13,
      "rating_method": "sequential_elo",
      "raw_elo": 1422.7603793686078,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.231216213725585,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 89.8806209562122,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-23T05:19:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1347.246671542211,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.807525230813738,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 73,
      "max_score": null,
      "measured_at": "2026-08-22T23:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1274.046932999176,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 16.6420903975188,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 104,
      "max_score": null,
      "measured_at": "2026-08-22T17:42:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1155.0432979180157,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-05T03:47:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1580.248490406413,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.24795980739564,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 82,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-05T03:54:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1554.25942083376,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.301004509305145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.144085005109797,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-07-31T02:32:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.309666305548,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.87509260752541,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 78,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-23T04:48:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.264516335169,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.172469636670904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 60,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-05T02:20:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1522.5585709646791,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.936775078827324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 252,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 95,
      "draws": 154,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-23T01:51:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 246,
      "rating_method": "sequential_elo",
      "raw_elo": 1510.3930229925163,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.73973256856557,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.1524206416837046,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-22T13:00:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.857410286727,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.558687152271936,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.3498876524732,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.14362212889749,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 98,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-07-31T02:31:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.192769921518,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.04295247255884,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 19.459772198068393,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T03:47:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.501959438092,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.77828780767661,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-21T20:36:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.6521530811533,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.552941865834306,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-05T01:02:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.3027736844938,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.00299359107813,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 59,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.6960155718434,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.6936216942447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 20.96867677046422,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 90,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.6944633151002,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.59443860612531,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-05T02:13:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.8875603348063,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.551305110490894,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1485.9572707576879,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.45363557593279,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 266,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 99,
      "draws": 206,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 266,
      "rating_method": "sequential_elo",
      "raw_elo": 1473.6315748334123,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.25224242939918,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-05T03:48:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.3450286460047,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.070339654447714,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 10
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 50,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-07-30T18:04:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 50,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.3591546604298,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.58942946961961,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 26.264004201400486,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-21T20:01:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.8932821904841,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.20889098134736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T05:24:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1469.0718049538236,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.01263971429604,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1463.4540362928522,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.05506647400019,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-04T23:28:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1467.7918733909657,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.89168262273526,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 156,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 76,
      "draws": 105,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-05T03:47:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 156,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.7466794854122,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.1685979425594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.51792189268726,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-05T00:50:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1443.1168128216952,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.71863054561698,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 127,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 91,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 127,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.7661524468779,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.63833030232732,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.444173824159213,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 83,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 42,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-22T04:12:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 83,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.908837049594,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.67026413949224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.804472558998102,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 22,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 11,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-23T01:51:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 22,
      "rating_method": "sequential_elo",
      "raw_elo": 1459.6299005995513,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.50886244123093,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 60.5072070285374,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-23T12:24:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.7350302187187,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.86522222010667,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-03T14:54:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.1892220782775,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.501934434108996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 50,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-23T02:43:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1214.9205299918149,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 99,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1963.1321087145507,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 90.96243393579934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.251875136730032,
      "unilateral_faults": 0,
      "wins": 181
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-22T14:19:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1727.8905474681214,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 65.33787445900813,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 179,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 74,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-08-20T13:06:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 179,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.7293692690507,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.50627032058176,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-08-03T10:29:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.5922874284433,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.399729153600475,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-31T02:29:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1615.3072002247638,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.683472652436585,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-08-05T00:20:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1591.7468690047804,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.87934682152756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.259934288992827,
      "unilateral_faults": 0,
      "wins": 113
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 42,
      "max_score": null,
      "measured_at": "2026-08-20T12:15:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.2966805223457,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.59420148801351,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-15T02:19:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1576.611974494223,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.581984750264844,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-03T14:14:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1564.6607990856423,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.20092432661375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.9642531639468,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.951577978721,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 335,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 130,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 144,
      "max_score": null,
      "measured_at": "2026-08-22T23:45:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 335,
      "rating_method": "sequential_elo",
      "raw_elo": 1516.0026260489992,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.197554884890174,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 191
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-04T23:21:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1525.507550969813,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.175510141908525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 36,
      "max_score": null,
      "measured_at": "2026-08-22T11:11:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.479690855548,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.525392048416236,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 73,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1519.7914352128794,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.134814130021056,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.570138866854082,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 230,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 115,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 114,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 230,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.8763793004314,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.80751645753057,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.048814933939525,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 157,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 81,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 157,
      "rating_method": "sequential_elo",
      "raw_elo": 1486.7110311244185,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.519868263300424,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-05T01:37:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.0462009965422,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.468260024253375,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-08-03T11:29:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.7266136050657,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.68105445209972,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-03T11:38:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1470.0736718738399,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.40888752062887,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1501.807691416014,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.08609625332008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.8875852525139,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.17279269378332,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-08-03T12:50:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.2526700075625,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.763744651369436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-03T11:37:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1411.1338655756442,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.936055258537635,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-03T14:20:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1388.5924060058305,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.940983948757605,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-08-22T14:19:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1367.3392576198007,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.10005925612763,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:mistralai-mistral-medium-3-5:34da7964c6511272",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-03T11:38:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1366.1081717055815,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.950977461561465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1334.1173082540881,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.19854110959529,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 206,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 135,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 206,
      "rating_method": "sequential_elo",
      "raw_elo": 1320.182645360226,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.124865522470365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.2943419813913195,
      "unilateral_faults": 0,
      "wins": 71
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 152,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-08-22T10:50:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 148,
      "rating_method": "sequential_elo",
      "raw_elo": 1311.3355817153363,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.914142734486916,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-08-05T03:40:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1289.417656335887,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.078992764114222,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-08-22T10:50:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1285.0923577468707,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.820653512829104,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-20T12:05:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1277.8106711339308,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.725327714421983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 83,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 128,
      "max_score": null,
      "measured_at": "2026-08-05T04:56:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1177.5020483483413,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.10631739223014,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.807372224754609,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemini-3-1-flash-lite:483a08d2c98ab52c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-07-31T03:34:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1154.0769237728996,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.808040655611663,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-08-05T02:32:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1147.5879156708982,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.568992620174647,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1146.4306765922527,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.508036486618778,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 85,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 124,
      "max_score": null,
      "measured_at": "2026-08-03T22:34:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1134.3619315082324,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.33176752068492,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.19101199758159,
      "unilateral_faults": 4,
      "wins": 46
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 181,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 148,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 181,
      "rating_method": "sequential_elo",
      "raw_elo": 1100.5438465639747,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 15.533730958964114,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 324,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 118,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 277,
      "max_score": null,
      "measured_at": "2026-08-22T19:33:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 324,
      "rating_method": "sequential_elo",
      "raw_elo": 1046.1571521330118,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 10.571254109747576,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1957.933835666878,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 89.17064281296983,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-20T18:11:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1788.6250256792016,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 75.15416974608023,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 74
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-03T11:04:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1692.7406046026997,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 66.56206174162008,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 93,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-22T11:41:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1665.5047561892463,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 64.73769106673069,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 62
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 176,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-08-20T21:14:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1633.7663053252722,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.0083250910945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 91
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 292,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 108,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 112,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 292,
      "rating_method": "sequential_elo",
      "raw_elo": 1630.5056153716068,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 62.48746584354412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 176
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1612.7137751991481,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.57776973557898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.466769200052298,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-05T01:59:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1590.5886286061254,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.20947020939446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 31,
      "max_score": null,
      "measured_at": "2026-08-03T13:58:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1572.6488159742216,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.74330710655394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1529.0020375469994,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.100496566401134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.026656325279454,
      "unilateral_faults": 0,
      "wins": 99
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 159,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-08-22T18:02:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 159,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.5552783412897,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.928109855002525,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-08-20T21:54:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.3777590913119,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.921447482930446,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.4830994560295,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.03537257988135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 198,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 97,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 97,
      "max_score": null,
      "measured_at": "2026-08-05T04:32:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 198,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.509690149318,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.921378822609434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.47889689397148,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.8627003840757,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.5973483966481,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 240,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 118,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 120,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 240,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.4041965506742,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.817382769259154,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.049007825231694,
      "unilateral_faults": 0,
      "wins": 117
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1487.8317645204697,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.56381339180203,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-08-03T09:47:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.7039967938965,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.498198272140634,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 49
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 49,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1393.1904394516557,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.83680633654252,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemini-3-1-flash-lite:483a08d2c98ab52c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-07-31T02:02:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.718765099697,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.31086220995625,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-03T12:29:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.5359335828546,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.20986690104408,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:mistralai-mistral-medium-3-5:34da7964c6511272",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-05T00:42:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1341.437842566501,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.28354233376265,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.1475676513953,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.1510974048913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-05T00:42:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.778953761991,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.00479516375429,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 21,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-23T00:33:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 21,
      "rating_method": "sequential_elo",
      "raw_elo": 1371.625457434903,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.298263426455435,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 62.850358177805205,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 325,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 212,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 325,
      "rating_method": "sequential_elo",
      "raw_elo": 1266.9834845152213,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.035368345546885,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-22T23:34:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.7844100164866,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.28416015452614,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-08-20T21:45:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1260.4296004941673,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.66305165235034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 93,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 66,
      "max_score": null,
      "measured_at": "2026-08-05T03:19:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.1713265502815,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.370496584013946,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-07-31T00:54:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1261.0646377191872,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.283145533114592,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 60,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1238.9945909503178,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.822041323047518,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 50,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1233.8513345112337,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.594696782513516,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-08-05T03:20:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1212.912535347638,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.46626922181831,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-08-22T23:34:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1202.0009439276766,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.70848810998782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 165,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 118,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 165,
      "rating_method": "sequential_elo",
      "raw_elo": 1191.2017859373725,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.677590362951314,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 115,
      "max_score": null,
      "measured_at": "2026-08-20T21:45:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1163.5476894293736,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.342189962527502,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 63,
      "max_score": null,
      "measured_at": "2026-08-05T03:19:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1139.6621346195743,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.257450141021867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 18
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 242,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 94,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 184,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 242,
      "rating_method": "sequential_elo",
      "raw_elo": 1095.9852006337294,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.22866796894646,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 1.5190135939585359,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-03T14:13:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1824.0062989974588,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 81.36870015249958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 142,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-22T14:34:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 142,
      "rating_method": "sequential_elo",
      "raw_elo": 1764.6335863223985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 76.29165283136004,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 290,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 94,
      "max_score": null,
      "measured_at": "2026-08-22T15:50:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 290,
      "rating_method": "sequential_elo",
      "raw_elo": 1732.781357799889,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 73.02102977984342,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 196
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-03T08:56:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1704.7019054474856,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.87219421844685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-08-03T10:15:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.6540509725637,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.528190114310334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-05T01:45:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1575.9166268461142,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.619553407262025,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 309,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 113,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 144,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 305,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.4751430308143,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.01429727686298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 161
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 59,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.8790445826737,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.99459166857962,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-03T14:04:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.8690234891826,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.65187154398772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 93,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-22T19:47:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1548.3599516347117,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.034378723576836,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 56
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:xiaomi-mimo-v2-5-pro:df1c628cc31cb288",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5-Pro",
      "model_slug": "xiaomi-mimo-v2-5-pro",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1549.490807576366,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.982816468950794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 186,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 88,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 99,
      "max_score": null,
      "measured_at": "2026-08-04T01:46:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.060781937911,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.39005509336917,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.957067918206963,
      "unilateral_faults": 0,
      "wins": 79
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 124,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 62,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 65,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 124,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.9395388467756,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.209975643465064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 19.267903630526114,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 19,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 10,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-23T02:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 19,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.254789411236,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.16395464120409,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 68.05339887498948,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-05T01:37:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1488.6293568171732,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.901696725852915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-05T04:02:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.6571114899198,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.145052128337795,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-03T12:28:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.05224599759,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.8080936476681,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 190,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 93,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 93,
      "max_score": null,
      "measured_at": "2026-08-05T05:16:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 190,
      "rating_method": "sequential_elo",
      "raw_elo": 1432.7430806795305,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.07920799575945,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.283112930469331,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-03T12:43:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.3690275885945,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.395576864441175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-23T12:27:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.0816236736982,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.64180228110675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-19T21:31:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.0330257928692,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.35125414343914,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 65,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 105,
      "max_score": null,
      "measured_at": "2026-08-23T10:07:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.9568971055057,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.0307879145991,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-08-05T04:09:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1380.3193424919139,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.262658898597685,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 32
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-08-19T21:22:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1375.6943937413528,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.18021347469483,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 11,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.4252730885935,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.525553812172575,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-03T00:20:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1357.2220634238477,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.80737392306428,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.4372322496993,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.543087970431298,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-05T04:09:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1335.8860586083808,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.09131527235869,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 79,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 90,
      "max_score": null,
      "measured_at": "2026-08-03T22:56:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1338.8129674710015,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.92571274446921,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.154975300928378,
      "unilateral_faults": 2,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-08-03T11:10:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1323.4878955652127,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.717577482950762,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 118,
      "max_score": null,
      "measured_at": "2026-08-19T21:34:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1295.2414425828902,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.888932528351898,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 180,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:cohere-north-mini-code:3e6a1897cfdaa330",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 82,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 123,
      "max_score": null,
      "measured_at": "2026-08-05T02:50:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 176,
      "rating_method": "sequential_elo",
      "raw_elo": 1278.282398636208,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.88114022139318,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.29009959559265,
      "unilateral_faults": 4,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-03T21:49:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1224.0896973580377,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.047634614739106,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 2,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 79,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1151.7537351331357,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 11.847787789192054,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1144.6688037728486,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 10.490412921476183,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 138,
      "max_score": null,
      "measured_at": "2026-08-22T14:34:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1114.7430613418464,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 9.05968322587179,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 24
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 69,
      "max_score": null,
      "measured_at": "2026-08-04T01:46:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1108.5181051201985,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 7.108412173273799,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 2,
      "wins": 13
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:qwen-qwen3-7-plus:a8d8ab3b2b52478f",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-plus",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 61,
      "max_score": null,
      "measured_at": "2026-08-04T01:12:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Plus",
      "model_slug": "qwen-qwen3-7-plus",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1075.8218147652353,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-plus",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 3.600933227553536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 2,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:baseline:google-gemini-3-1-flash-lite:483a08d2c98ab52c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-07-31T03:28:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1044.278117743902,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:moonshotai-kimi-k3:5a54aec150052f73",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 67,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 2018.027571089958,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 98.88106339111127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 168,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:x-ai-grok-4-5:0d820700fd8c1f0b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 69,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-22T18:02:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 168,
      "rating_method": "sequential_elo",
      "raw_elo": 1890.764208012442,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 85.5368320379681,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 142
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-sol:34bccf96d771d2e5",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-22T23:22:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1801.5518334727867,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 75.08894239706439,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 69
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-4-8:78901219e94b3137",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-03T04:47:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1792.8722395599843,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 73.81276758326433,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-4-5:5c9da2cc66629f89",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-03T01:17:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1757.3352174883826,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking field omitted",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking field omitted",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking field omitted",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 70.0969711174775,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:thinkingmachines-inkling:70a9ac993f011430",
      "capped_draws": 7,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 7,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T03:33:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1741.2522481037183,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.95924601863939,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 258,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-opus-5:e9ebdf808117b870",
      "capped_draws": 14,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 110,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-08-21T15:53:02Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 258,
      "rating_method": "sequential_elo",
      "raw_elo": 1724.7767888250444,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.65894839210796,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.0009297552497305,
      "unilateral_faults": 0,
      "wins": 190
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:meta-muse-spark-1-2:772fc6bb6f83c6c9",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-21T18:12:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.41020376169,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.44710258784996,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:z-ai-glm-5-2:79cd8062a2dce9fb",
      "capped_draws": 54,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 64,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-07-31T20:23:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.7519312912373,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.193398652066804,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 18.466769200052298,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:deepseek-deepseek-v4-pro:e8d00a0b6ffa9a25",
      "capped_draws": 73,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 73,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-03T03:56:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1515.051856910287,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.222502598035426,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:minimax-minimax-m3:214bcd6c65e8f3eb",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "minimax/minimax-m3",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-02T23:32:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Minimax M3",
      "model_slug": "minimax-minimax-m3",
      "plugin_success_rate": null,
      "provider": "MiniMax",
      "provider_key": "minimax",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1506.4645617409897,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "minimax",
        "provider_model": "minimax/minimax-m3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.03473455786694,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4-nano:6279438894c15a9b",
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 85,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-nano",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Nano",
      "model_slug": "gpt-5-4-nano",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.1120170443423,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-nano",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.07682565953572,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.243458840961587,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:claude-sonnet-5:5d48f6168d64e7fe",
      "capped_draws": 34,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 34,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-15T01:49:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.1322671330724,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Thinking disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "Thinking disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Thinking disabled",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.54296563169207,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-8-max:3a653d034173d2f2",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 7,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-21T20:35:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1535.547974554364,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.46830457086832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-5:f6e479886e809751",
      "capped_draws": 76,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 76,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T01:22:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1429.3708835943642,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.263590475601305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:tencent-hy3-preview:569c7bc7bedf8ce3",
      "capped_draws": 83,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 83,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:32:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1424.9981872068206,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.009683345730224,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:nvidia-nemotron-3-ultra-550b-a55b:a987a47e59219899",
      "capped_draws": 68,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-31T02:32:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1430.840451333209,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.7686972873823,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemma-4-31b-it:e747a6997aa21289",
      "capped_draws": 82,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 82,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemma-4-31b-it",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-04T22:07:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemma 4 31B",
      "model_slug": "google-gemma-4-31b-it",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1419.8830391614035,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemma-4-31b-it",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.474836925823645,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:deepseek-deepseek-v4-flash:423951efbfeea85e",
      "capped_draws": 80,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 80,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:55:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1416.8224215244215,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.0364485323938,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:nex-agi-nex-n2-pro:2f1571320c21662f",
      "capped_draws": 87,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 87,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nex-agi/nex-n2-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-05T04:41:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nex N2 Pro",
      "model_slug": "nex-agi-nex-n2-pro",
      "plugin_success_rate": null,
      "provider": "Nex AGI",
      "provider_key": "nex-agi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.5476658850525,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nex-agi",
        "provider_model": "nex-agi/nex-n2-pro",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.23396365548673,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-4-1:4599845cc619bbdb",
      "capped_draws": 72,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 72,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-4.1",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "omitted",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 4.1",
      "model_slug": "gpt-4-1",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.8185070181821,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-4.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "omitted",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "omitted",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.05316059344751,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:cohere-north-mini-code:3e6a1897cfdaa330",
      "capped_draws": 86,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 86,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "cohere/north-mini-code",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T03:33:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "North Mini Code",
      "model_slug": "cohere-north-mini-code",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1403.7240598409555,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "cohere/north-mini-code",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.85875457644092,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 3.707899787624953,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4-mini:1967d37331d30497",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4-mini",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-04T06:58:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4 Mini",
      "model_slug": "gpt-5-4-mini",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1407.788041459873,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4-mini",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.54787145753626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 2,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 208,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:meituan-longcat-2-0:8409ccd1edce8105",
      "capped_draws": 181,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 98,
      "draws": 181,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meituan/longcat-2.0",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-05T04:49:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "LongCat 2.0",
      "model_slug": "meituan-longcat-2-0",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 208,
      "rating_method": "sequential_elo",
      "raw_elo": 1389.5031523076473,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meituan/longcat-2.0",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.25995087039648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-terra:667397b0870c7a77",
      "capped_draws": 64,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 64,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-04T07:10:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.9303824976794,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.16201019317678,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 2,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 14,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:thinkingmachines-inkling-small:2a1c609d5f09a424",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 6,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-21T20:35:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 14,
      "rating_method": "sequential_elo",
      "raw_elo": 1452.7060664706091,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.15114034501958,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 214,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:poolside-laguna-s-2-1:834cbfa8b37e299a",
      "capped_draws": 179,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 101,
      "draws": 179,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "poolside/laguna-s-2.1",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Laguna S 2.1",
      "model_slug": "poolside-laguna-s-2-1",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 214,
      "rating_method": "sequential_elo",
      "raw_elo": 1387.5631121202853,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "poolside/laguna-s-2.1",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.11405727592425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.364069356670375,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 288,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:inclusionai-ling-3-0-flash:4838b994eb665922",
      "capped_draws": 244,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 107,
      "draws": 244,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "unknown_legacy",
        "effective_request_value": "baseline",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "inclusionai/ling-3.0-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "unknown_legacy",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ling 3.0 Flash",
      "model_slug": "inclusionai-ling-3-0-flash",
      "plugin_success_rate": null,
      "provider": "InclusionAI",
      "provider_key": "inclusionai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 284,
      "rating_method": "sequential_elo",
      "raw_elo": 1374.3105536667902,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Baseline track (legacy evidence incomplete)",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "inclusionai",
        "provider_model": "inclusionai/ling-3.0-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "request_mode": null,
          "requested_effort": null,
          "source": "versioned_reasoning_capability_catalog",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "unknown_legacy",
        "provider_setting_label": null,
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Baseline",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": null,
        "requested_reasoning_effort": "baseline"
      },
      "reasoning_setting": null,
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.255249763757412,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:qwen-qwen3-7-max:aa6ab832c76ea81e",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.7-max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-05T05:33:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.7 Max",
      "model_slug": "qwen-qwen3-7-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1379.4580243708433,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.7-max",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.087752265854334,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 334,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-6-flash:497c5e32f5a0da50",
      "capped_draws": 226,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 123,
      "draws": 226,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 92,
      "max_score": null,
      "measured_at": "2026-08-23T00:15:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 334,
      "rating_method": "sequential_elo",
      "raw_elo": 1364.1951020946215,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.468489170149333,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 106,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:mistralai-mistral-medium-3-5:34da7964c6511272",
      "capped_draws": 87,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 87,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T04:49:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 106,
      "rating_method": "sequential_elo",
      "raw_elo": 1368.2539193575665,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.076430145642476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 4.586824452283178,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 95,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-4:86f20e721b83e093",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 95,
      "rating_method": "sequential_elo",
      "raw_elo": 1369.526850657215,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.98416128073413,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 7.281036307982882,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 331,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:google-gemini-3-5-flash-lite:d8ea2a1333ff0452",
      "capped_draws": 225,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 121,
      "draws": 225,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "minimal",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 92,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 331,
      "rating_method": "sequential_elo",
      "raw_elo": 1350.3683142272248,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Minimal",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "minimal",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Minimal",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Minimal",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "minimal"
      },
      "reasoning_setting": "minimal",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 29.008271779974574,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 157,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:o3:647217df3b12bb67",
      "capped_draws": 105,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 105,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 47,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 157,
      "rating_method": "sequential_elo",
      "raw_elo": 1346.5104644614696,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.51885536161832,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:xiaomi-mimo-v2-5:bc21a02f757e23f7",
      "capped_draws": 120,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 83,
      "draws": 120,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "toggle",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 44,
      "max_score": null,
      "measured_at": "2026-08-05T05:41:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1353.8058692077334,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Reasoning disabled",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "toggle",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Reasoning disabled",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Reasoning disabled",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "toggle",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.04343856526308,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 10.830591148722647,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:stealth-ox-alpha:2a6c37bfc1ea9a10",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1398.0853900991224,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.439932585091782,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:stepfun-step-3-7-flash:283efeb922617cca",
      "capped_draws": 99,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 99,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.5376746549155,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 22.799140452263753,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 150,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:openai-gpt-oss-120b:bd210de776e73710",
      "capped_draws": 89,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 89,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "low",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-08-23T02:22:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 150,
      "rating_method": "sequential_elo",
      "raw_elo": 1270.6137277486175,
      "reasoning_bracket": "baseline",
      "reasoning_level": "Low",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "low",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Low",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "Low",
        "reasoning_catalog_sha256": "36e6474531ff8756094c0f4fdb565c125aedb076d2fdad9942a6360ec6adbd7c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "low"
      },
      "reasoning_setting": "low",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.506744531570664,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:baseline:gpt-5-6-luna:1c8c41335b2357b1",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "none",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 74,
      "max_score": null,
      "measured_at": "2026-08-22T11:52:09Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1083.8717985479768,
      "reasoning_bracket": "baseline",
      "reasoning_level": "None",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "baseline",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "none",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/baseline"
        },
        "provider_route": "openai",
        "provider_setting_label": "None",
        "reasoning_bracket": "baseline",
        "reasoning_bucket": "baseline",
        "reasoning_bucket_label": "None",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "none"
      },
      "reasoning_setting": "none",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 0.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/baseline",
      "track_name": "Baseline filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 686,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 3,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 1.17244375,
        "mean": 0.7965692187500001,
        "median": 0.7419175,
        "min": 0.6308437499999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 6.372553750000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 87.33240524426331,
      "contributing_entrants": null,
      "distinct_rated_opponents": 22,
      "draws": 31,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:27:52Z",
      "losses": 70,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 63.917443301992066,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 1,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 686,
      "rating_method": "sequential_elo",
      "raw_elo": 1847.0273809657585,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 87.33240524426331,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 585
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 604,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 1.91725,
        "mean": 1.58262125,
        "median": 1.5854,
        "min": 1.05322,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 12.660969999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 83.32037116335817,
      "contributing_entrants": null,
      "distinct_rated_opponents": 36,
      "draws": 72,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "infra_failures_excluded": 4,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:44:21Z",
      "losses": 91,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 67.5967962093199,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 2,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 604,
      "rating_method": "sequential_elo",
      "raw_elo": 1839.8742026911013,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 83.32037116335817,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 441
    },
    {
      "admitted_plugins": 13,
      "attempted_matches": 778,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 1,
      "codegen_cost_usd": {
        "admitted_cell_count": 13,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 16
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 3,
        "max": 2.09943,
        "mean": 1.379653125,
        "median": 1.3205149999999999,
        "min": 0.8875599999999999,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-25": 16
        },
        "run_count": 16,
        "token_priced_attempt_count": 16,
        "total": 22.074450000000002
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 80.00582303982328,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 52,
      "eligibility_flag": true,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.8125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:44:12Z",
      "losses": 140,
      "max_score": 100.0,
      "measured_at": null,
      "min_score": 58.28936991672205,
      "model_code_failure_rate": 0.1875,
      "model_code_failures": 3,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": 0.8125,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 3,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 778,
      "rating_method": "sequential_elo",
      "raw_elo": 1807.1235611426816,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 75.95868536285322,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 586
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 642,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 15,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 2.2530275,
        "mean": 1.51903,
        "median": 1.4938600000000002,
        "min": 1.088255,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 12.15224
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 75.18390389272452,
      "contributing_entrants": null,
      "distinct_rated_opponents": 21,
      "draws": 84,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T08:04:25Z",
      "losses": 74,
      "max_score": 95.06137796160141,
      "measured_at": null,
      "min_score": 38.881693886910185,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 4,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 639,
      "rating_method": "sequential_elo",
      "raw_elo": 1792.2939944421476,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 72.71548175880062,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 481
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 545,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 40,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 4.4173,
        "mean": 2.7356843750000004,
        "median": 2.536595,
        "min": 2.045485,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 21.885475
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 69.79119288611703,
      "contributing_entrants": null,
      "distinct_rated_opponents": 36,
      "draws": 107,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02"
      ],
      "first_pass_admitted": 7,
      "first_pass_rate": 0.875,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:35:52Z",
      "losses": 115,
      "max_score": 93.82012264656494,
      "measured_at": null,
      "min_score": 31.278757459984458,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": 0.875,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 5,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 544,
      "rating_method": "sequential_elo",
      "raw_elo": 1748.5057765730885,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 67.49982310677103,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 322
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 572,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 9
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 1.38945,
        "mean": 0.93123625,
        "median": 0.95991,
        "min": 0.36561,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 8,
        "token_priced_attempt_count": 9,
        "total": 7.449889999999999
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 68.9074703488038,
      "contributing_entrants": null,
      "distinct_rated_opponents": 37,
      "draws": 71,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:23:19Z",
      "losses": 146,
      "max_score": 79.45887582150341,
      "measured_at": null,
      "min_score": 53.60093706896381,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 1,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": 0.875,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 6,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 572,
      "rating_method": "sequential_elo",
      "raw_elo": 1706.0432881530799,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 1,
      "repaired_rate": 0.125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 66.64511476210285,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 355
    },
    {
      "admitted_plugins": 12,
      "attempted_matches": 1728,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 190,
      "codegen_cost_usd": {
        "admitted_cell_count": 12,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 4,
        "max": 0.531673125,
        "mean": 0.47737264687500003,
        "median": 0.48302475,
        "min": 0.3855675,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 7.6379623500000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 67.94613426450412,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 285,
      "eligibility_flag": true,
      "entry_count": 12,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-07"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.5,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:51:05Z",
      "losses": 436,
      "max_score": 91.56194509481253,
      "measured_at": null,
      "min_score": 48.9850812289486,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 4,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 7,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1724,
      "rating_method": "sequential_elo",
      "raw_elo": 1695.9244161237407,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 4,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 63.2310027037512,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 1003
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1220,
      "canonical_public_row_identity": "publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 42,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 11
        },
        "evidence_basis": "Provider-reported",
        "max": 0.13495079999999998,
        "mean": 0.07455065,
        "median": 0.0607138,
        "min": 0.0448404,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "recorded_attempt_count": 11,
        "run_count": 8,
        "total": 0.5964052000000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 62.11035404695588,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 233,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:27:52Z",
      "losses": 327,
      "max_score": 91.324739517719,
      "measured_at": null,
      "min_score": 32.41381726074275,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": 1.0,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": 8,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1220,
      "rating_method": "sequential_elo",
      "raw_elo": 1658.199093444562,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 62.11035404695588,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 660
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 602,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 44,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 11
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 12.137519999999999,
        "mean": 8.1660015625,
        "median": 8.18098,
        "min": 4.7142525,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 11
        },
        "run_count": 8,
        "token_priced_attempt_count": 11,
        "total": 65.3280125
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 57.52510803929284,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 137,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.625,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 8,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:35:30Z",
      "losses": 185,
      "max_score": 76.39149789263541,
      "measured_at": null,
      "min_score": 41.41290592375142,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 9,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 602,
      "rating_method": "sequential_elo",
      "raw_elo": 1622.7319965637296,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 57.52510803929284,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 280
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 684,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 13,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.50466,
        "mean": 0.35099375,
        "median": 0.321349,
        "min": 0.220732,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 2.80795
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 54.29911281921975,
      "contributing_entrants": null,
      "distinct_rated_opponents": 21,
      "draws": 160,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:13:25Z",
      "losses": 198,
      "max_score": 83.58905380078096,
      "measured_at": null,
      "min_score": 18.648854275319852,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": 10,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 684,
      "rating_method": "sequential_elo",
      "raw_elo": 1588.3322245131312,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 54.29911281921975,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 326
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 682,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 53,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 8
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.0377622,
        "mean": 0.030833324999999998,
        "median": 0.031411375,
        "min": 0.0247604,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 8
        },
        "run_count": 8,
        "token_priced_attempt_count": 8,
        "total": 0.24666659999999996
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 52.76207198216008,
      "contributing_entrants": null,
      "distinct_rated_opponents": 21,
      "draws": 200,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T08:55:05Z",
      "losses": 175,
      "max_score": 83.09168848413222,
      "measured_at": null,
      "min_score": 24.22675683362329,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 11,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 681,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.9767875156494,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 52.76207198216008,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 306
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 466,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "capped_draws": 58,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 18
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.6921525,
        "mean": 0.48907706250000005,
        "median": 0.483741,
        "min": 0.401826,
        "recorded_attempt_count": 18,
        "run_count": 8,
        "total": 3.9126165000000004
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 50.77386093048303,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 133,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:04:52Z",
      "losses": 168,
      "max_score": 80.84833683146083,
      "measured_at": null,
      "min_score": 24.174721344647317,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": 0.75,
      "provider": "Google",
      "provider_key": "google",
      "rank": 12,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 466,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.3773057677736,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 6,
      "repaired_rate": 0.75,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 47.25040169728176,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 165
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 514,
      "canonical_public_row_identity": "publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "capped_draws": 74,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 16
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.10909930499999998,
        "mean": 0.082847753875,
        "median": 0.084146916,
        "min": 0.03951746,
        "recorded_attempt_count": 16,
        "run_count": 8,
        "total": 0.6627820310000001
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 49.79095279932275,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 125,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:41Z",
      "losses": 201,
      "max_score": 77.21666620850746,
      "measured_at": null,
      "min_score": 32.98184099437737,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": 0.75,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 13,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 514,
      "rating_method": "sequential_elo",
      "raw_elo": 1538.202012164198,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 46.33570261437304,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 188
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 641,
      "canonical_public_row_identity": "publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 68,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_standard_estimate": 10
        },
        "evidence_basis": "Standard list-price estimate",
        "max": 0.45464499999999997,
        "mean": 0.28201406249999994,
        "median": 0.2695775,
        "min": 0.17401125,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 10
        },
        "run_count": 8,
        "token_priced_attempt_count": 10,
        "total": 2.2561124999999995
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 46.24774896841963,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 193,
      "eligibility_flag": true,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.75,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:05:23Z",
      "losses": 230,
      "max_score": 67.70578978678658,
      "measured_at": null,
      "min_score": 19.976294071045,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": 1.0,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 14,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 640,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.120873679543,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.25,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 46.24774896841963,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 1,
      "wins": 217
    },
    {
      "admitted_plugins": 19,
      "attempted_matches": 2801,
      "canonical_public_row_identity": "publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 219,
      "codegen_cost_usd": {
        "admitted_cell_count": 19,
        "cell_count": 8,
        "cost_basis_counts": {
          "estimated": 32,
          "local_standard_estimate": 8
        },
        "evidence_basis": "Combined: Recorded attempt + Standard list-price estimate",
        "failed_cell_count": 13,
        "max": 0.1097735,
        "mean": 0.091486,
        "median": 0.08840574999999999,
        "min": 0.0773785,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 40
        },
        "recorded_attempt_count": 32,
        "run_count": 32,
        "token_priced_attempt_count": 8,
        "total": 2.927552
      },
      "codegen_evaluated_cells": 32,
      "conditional_success_score": 48.78091738661657,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 282,
      "eligibility_flag": true,
      "entry_count": 19,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 19,
      "first_pass_rate": 0.59375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T13:45:04Z",
      "losses": 1224,
      "max_score": 56.03900598894137,
      "measured_at": null,
      "min_score": 39.158820258821116,
      "model_code_failure_rate": 0.40625,
      "model_code_failures": 13,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": 0.59375,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 15,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 2801,
      "rating_method": "sequential_elo",
      "raw_elo": 1509.7151807795326,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.82041472033598,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 1295
    },
    {
      "admitted_plugins": 6,
      "attempted_matches": 474,
      "canonical_public_row_identity": "publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "capped_draws": 87,
      "codegen_cost_usd": {
        "admitted_cell_count": 6,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0221782524,
        "mean": 0.00999808046,
        "median": 0.009941171,
        "min": 0.00212373,
        "recorded_attempt_count": 14,
        "run_count": 8,
        "total": 0.07998464368
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 41.58875401302814,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 135,
      "eligibility_flag": true,
      "entry_count": 6,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 3,
      "first_pass_rate": 0.375,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:43:54Z",
      "losses": 186,
      "max_score": 72.31048780319064,
      "measured_at": null,
      "min_score": 24.79810278001538,
      "model_code_failure_rate": 0.25,
      "model_code_failures": 2,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": 0.75,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": 16,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 474,
      "rating_method": "sequential_elo",
      "raw_elo": 1475.7097643914842,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 3,
      "repaired_rate": 0.375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 38.70269656852593,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 14,
      "attempted_matches": 1790,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 132,
      "codegen_cost_usd": {
        "admitted_cell_count": 14,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 50
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.0719635,
        "mean": 0.060768406250000004,
        "median": 0.0604727,
        "min": 0.05086675,
        "recorded_attempt_count": 50,
        "run_count": 16,
        "total": 0.9722945000000001
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.646037321732905,
      "contributing_entrants": null,
      "distinct_rated_opponents": 34,
      "draws": 435,
      "eligibility_flag": true,
      "entry_count": 13,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02"
      ],
      "first_pass_admitted": 13,
      "first_pass_rate": 0.8125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:38:06Z",
      "losses": 812,
      "max_score": 54.3795837338173,
      "measured_at": null,
      "min_score": 26.141806979414127,
      "model_code_failure_rate": 0.125,
      "model_code_failures": 2,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": 0.875,
      "provider": "Google",
      "provider_key": "google",
      "rank": 17,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1789,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.5539477718055,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 1,
      "repaired_rate": 0.0625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 35.44288232495812,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 542
    },
    {
      "admitted_plugins": 7,
      "attempted_matches": 554,
      "canonical_public_row_identity": "publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 41,
      "codegen_cost_usd": {
        "admitted_cell_count": 7,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.007539277999999999,
        "mean": 0.0032457859375,
        "median": 0.0019568429999999998,
        "min": 0.001266762,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 0.031586439
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 37.22073036163209,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 134,
      "eligibility_flag": true,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05"
      ],
      "first_pass_admitted": 5,
      "first_pass_rate": 0.5555555555555556,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:51Z",
      "losses": 244,
      "max_score": 59.334280478082064,
      "measured_at": null,
      "min_score": 13.456150792860978,
      "model_code_failure_rate": 0.2222222222222222,
      "model_code_failures": 2,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": 0.7777777777777778,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": 18,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 552,
      "rating_method": "sequential_elo",
      "raw_elo": 1449.614172560139,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.95415224018846,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 2,
      "wins": 174
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 368,
      "canonical_public_row_identity": "publication-row.v1:intensive:openai-gpt-oss-120b:707f3723f9845847",
      "capped_draws": 61,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.01660212,
        "mean": 0.008820586750000001,
        "median": 0.007023681,
        "min": 0.00271606,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.070564694
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 39.10085728904717,
      "contributing_entrants": null,
      "distinct_rated_opponents": 36,
      "draws": 151,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-05"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:11:31Z",
      "losses": 127,
      "max_score": 67.33768307109139,
      "measured_at": null,
      "min_score": 13.814065400064843,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": 0.625,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": 19,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 368,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.4188636801377,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 34.76612471599146,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 715,
      "canonical_public_row_identity": "publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 140,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 35
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.0456916,
        "mean": 0.031545040625,
        "median": 0.035551075,
        "min": 0.01864685,
        "recorded_attempt_count": 35,
        "run_count": 16,
        "total": 0.50472065
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 36.09170623264679,
      "contributing_entrants": null,
      "distinct_rated_opponents": 39,
      "draws": 303,
      "eligibility_flag": true,
      "entry_count": 9,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-03",
        "GB2-04",
        "GB2-06",
        "GB2-07"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.125,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:29:54Z",
      "losses": 259,
      "max_score": 46.15142583047198,
      "measured_at": null,
      "min_score": 19.686387180079826,
      "model_code_failure_rate": 0.4375,
      "model_code_failures": 7,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": 0.5625,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": 20,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 715,
      "rating_method": "sequential_elo",
      "raw_elo": 1440.5665099587284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 7,
      "repaired_rate": 0.4375,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 31.256334463397277,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 153
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 322,
      "canonical_public_row_identity": "publication-row.v1:intensive:xiaomi-mimo-v2-5:865be584a2f7aaf7",
      "capped_draws": 106,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0597184625,
        "mean": 0.02467013555,
        "median": 0.0239011175,
        "min": 0.0040410944,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.19736108440000003
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.81793203271081,
      "contributing_entrants": null,
      "distinct_rated_opponents": 37,
      "draws": 203,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-03",
        "GB2-05",
        "GB2-07"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-07-31T20:22:54Z",
      "losses": 74,
      "max_score": 58.591838652401584,
      "measured_at": null,
      "min_score": 17.329198413600206,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": 0.625,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": 21,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 322,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.805626528563,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 30.95800581695214,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 427,
      "canonical_public_row_identity": "publication-row.v1:intensive:google-gemini-3-1-flash-lite:ff56b3b6c0d25588",
      "capped_draws": 66,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 19
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.0422995,
        "mean": 0.027492531250000004,
        "median": 0.025548,
        "min": 0.0204145,
        "recorded_attempt_count": 19,
        "run_count": 8,
        "total": 0.21994025
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 34.434364323170016,
      "contributing_entrants": null,
      "distinct_rated_opponents": 38,
      "draws": 120,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T05:05:18Z",
      "losses": 220,
      "max_score": 46.38961044453501,
      "measured_at": null,
      "min_score": 20.711146730771695,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": 0.625,
      "provider": "Google",
      "provider_key": "google",
      "rank": 22,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 427,
      "rating_method": "sequential_elo",
      "raw_elo": 1363.8471843700231,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 30.616960536836054,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 427,
      "canonical_public_row_identity": "publication-row.v1:intensive:stepfun-step-3-7-flash:4da76a51b292ca95",
      "capped_draws": 69,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 20
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 3,
        "max": 0.11219570000000001,
        "mean": 0.0607572625,
        "median": 0.060057275,
        "min": 0.02174195,
        "recorded_attempt_count": 20,
        "run_count": 8,
        "total": 0.48605810000000005
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 32.74111651500159,
      "contributing_entrants": null,
      "distinct_rated_opponents": 37,
      "draws": 71,
      "eligibility_flag": true,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04"
      ],
      "first_pass_admitted": 0,
      "first_pass_rate": 0.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T03:50:20Z",
      "losses": 222,
      "max_score": 46.55383945263552,
      "measured_at": null,
      "min_score": 9.651433101795904,
      "model_code_failure_rate": 0.375,
      "model_code_failures": 3,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": 0.625,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": 23,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 427,
      "rating_method": "sequential_elo",
      "raw_elo": 1355.9232483701903,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 5,
      "repaired_rate": 0.625,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 29.11142668015633,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 134
    },
    {
      "admitted_plugins": 9,
      "attempted_matches": 1304,
      "canonical_public_row_identity": "publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 156,
      "codegen_cost_usd": {
        "admitted_cell_count": 9,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 53
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 7,
        "max": 0.302804525,
        "mean": 0.259828169375,
        "median": 0.2529231275,
        "min": 0.22308452,
        "recorded_attempt_count": 53,
        "run_count": 16,
        "total": 4.1572507100000005
      },
      "codegen_evaluated_cells": 16,
      "conditional_success_score": 31.625906752195938,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 396,
      "eligibility_flag": true,
      "entry_count": 9,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-01",
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "first_pass_admitted": 4,
      "first_pass_rate": 0.25,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T09:56:43Z",
      "losses": 647,
      "max_score": 60.52933478522943,
      "measured_at": null,
      "min_score": 15.649250107241665,
      "model_code_failure_rate": 0.4375,
      "model_code_failures": 7,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": 0.5625,
      "provider": "Other",
      "provider_key": "other",
      "rank": 24,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "ranked",
      "rated_matches": 1302,
      "rating_method": "sequential_elo",
      "raw_elo": 1372.7229374611602,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 5,
      "repaired_rate": 0.3125,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 27.38883866511949,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 259
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-row.v1:intensive:z-ai-glm-5-2:bc1714da76816a46",
      "capped_draws": 18,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 1,
        "cost_basis_counts": {
          "provider_reported": 7
        },
        "evidence_basis": "Provider-reported",
        "max": 0.09063263032999999,
        "mean": 0.09063263032999999,
        "median": 0.09063263032999999,
        "min": 0.09063263032999999,
        "recorded_attempt_count": 7,
        "run_count": 2,
        "total": 0.18126526065999998
      },
      "codegen_evaluated_cells": 2,
      "conditional_success_score": 53.3313100517875,
      "contributing_entrants": null,
      "distinct_rated_opponents": 17,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": 2,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 2,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T14:35:20Z",
      "losses": 64,
      "max_score": 53.3313100517875,
      "measured_at": null,
      "min_score": 53.3313100517875,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": 1.0,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.306297413937,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 53.3313100517875,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-row.v1:intensive:meta-muse-spark-1-2:8ed12b9970d2209b",
      "capped_draws": 11,
      "codegen_cost_usd": {
        "admitted_cell_count": 2,
        "cell_count": 2,
        "cost_basis_counts": {
          "provider_reported": 2
        },
        "evidence_basis": "Provider-reported",
        "max": 0.143734,
        "mean": 0.123945875,
        "median": 0.123945875,
        "min": 0.10415775,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 2
        },
        "recorded_attempt_count": 2,
        "run_count": 2,
        "total": 0.24789175
      },
      "codegen_evaluated_cells": 2,
      "conditional_success_score": 51.99337133367074,
      "contributing_entrants": null,
      "distinct_rated_opponents": 19,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": 2,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 2,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-04",
        "GB2-05",
        "GB2-06",
        "GB2-07",
        "GB2-08"
      ],
      "infra_failures_excluded": 6,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-21T11:42:50Z",
      "losses": 70,
      "max_score": 53.346963426005594,
      "measured_at": null,
      "min_score": 50.63977924133589,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.9666145030803,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 51.99337133367074,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 714,
      "canonical_public_row_identity": "publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 19,
      "codegen_cost_usd": {
        "admitted_cell_count": 5,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 15
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.6279041999999999,
        "mean": 0.526117125,
        "median": 0.5491332,
        "min": 0.330054,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 15
        },
        "recorded_attempt_count": 15,
        "run_count": 8,
        "total": 4.208937
      },
      "codegen_evaluated_cells": 7,
      "conditional_success_score": 53.2059313724767,
      "contributing_entrants": null,
      "distinct_rated_opponents": 33,
      "draws": 219,
      "eligibility_flag": false,
      "entry_count": 5,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-05",
        "GB2-06"
      ],
      "first_pass_admitted": 1,
      "first_pass_rate": 0.14285714285714285,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "generation_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-08"
      ],
      "infra_failures_excluded": 1,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T13:52:12Z",
      "losses": 173,
      "max_score": 80.95493130171027,
      "measured_at": null,
      "min_score": 23.78419992194771,
      "model_code_failure_rate": 0.2857142857142857,
      "model_code_failures": 2,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": 0.7142857142857143,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 714,
      "rating_method": "sequential_elo",
      "raw_elo": 1581.963152062793,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 4,
      "repaired_rate": 0.5714285714285714,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 48.91342129541595,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 322
    },
    {
      "admitted_plugins": 25,
      "attempted_matches": 337,
      "canonical_public_row_identity": "publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 10,
      "codegen_cost_usd": {
        "admitted_cell_count": 25,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 31
        },
        "evidence_basis": "Provider-reported",
        "max": 0.0,
        "mean": 0.0,
        "median": 0.0,
        "min": 0.0,
        "recorded_attempt_count": 31,
        "run_count": 28,
        "total": 0.0
      },
      "codegen_evaluated_cells": 25,
      "conditional_success_score": 44.31643372112509,
      "contributing_entrants": null,
      "distinct_rated_opponents": 1,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": 23,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 22,
      "first_pass_rate": 0.88,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-03"
      ],
      "infra_failures_excluded": 5,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T15:12:59Z",
      "losses": 81,
      "max_score": 52.06957808560736,
      "measured_at": null,
      "min_score": 35.26149604339514,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": 1.0,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 333,
      "rating_method": "sequential_elo",
      "raw_elo": 1558.5303719528429,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 3,
      "repaired_rate": 0.12,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 44.31643372112509,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 4,
      "wins": 191
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 1256,
      "canonical_public_row_identity": "publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 125,
      "codegen_cost_usd": {
        "admitted_cell_count": 15,
        "cell_count": 8,
        "cost_basis_counts": {
          "local_list_price_estimate": 17
        },
        "evidence_basis": "Standard list-price estimate",
        "failed_cell_count": 1,
        "max": 0.512955,
        "mean": 0.43048093750000005,
        "median": 0.4308725,
        "min": 0.32672249999999997,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-07-12": 8,
          "boardgame-list-prices-2026-08-08": 9
        },
        "run_count": 16,
        "token_priced_attempt_count": 17,
        "total": 6.887695
      },
      "codegen_evaluated_cells": 8,
      "conditional_success_score": 43.019970128414535,
      "contributing_entrants": null,
      "distinct_rated_opponents": 35,
      "draws": 351,
      "eligibility_flag": false,
      "entry_count": 8,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": 8,
      "first_pass_rate": 1.0,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-22T04:11:45Z",
      "losses": 447,
      "max_score": 65.20264997974215,
      "measured_at": null,
      "min_score": 13.078411737521655,
      "model_code_failure_rate": 0.0,
      "model_code_failures": 0,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": 1.0,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 1256,
      "rating_method": "sequential_elo",
      "raw_elo": 1495.5947734548256,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 43.019970128414535,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 458
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 129,
      "canonical_public_row_identity": "publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 12,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.40721066666666667,
        "mean": 0.3468699583333334,
        "median": 0.3476285,
        "min": 0.237408,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 13,
        "total": 4.659586000000001
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 44.78487833740139,
      "contributing_entrants": null,
      "distinct_rated_opponents": 14,
      "draws": 36,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-04"
      ],
      "first_pass_admitted": 8,
      "first_pass_rate": 0.8,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [
        "GB2-02",
        "GB2-06",
        "GB2-08"
      ],
      "infra_failures_excluded": 3,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T12:51:05Z",
      "losses": 29,
      "max_score": 68.66906686669674,
      "measured_at": null,
      "min_score": 20.752949450340513,
      "model_code_failure_rate": 0.2,
      "model_code_failures": 2,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": 0.8,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 129,
      "rating_method": "sequential_elo",
      "raw_elo": 1556.031618523617,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": 0,
      "repaired_rate": 0.0,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 42.35492289782546,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 64
    },
    {
      "admitted_plugins": 8,
      "attempted_matches": 117,
      "canonical_public_row_identity": "publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 17,
      "codegen_cost_usd": {
        "admitted_cell_count": 8,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 2,
        "max": 0.06806129999999999,
        "mean": 0.037113121874999995,
        "median": 0.0310111,
        "min": 0.0230335,
        "pricing_table_versions": {
          "boardgame-list-prices-2026-08-08": 14
        },
        "recorded_attempt_count": 14,
        "run_count": 10,
        "total": 0.38761484999999996
      },
      "codegen_evaluated_cells": 10,
      "conditional_success_score": 37.264078008031774,
      "contributing_entrants": null,
      "distinct_rated_opponents": 17,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": 7,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-04",
        "GB2-06"
      ],
      "first_pass_admitted": 6,
      "first_pass_rate": 0.6,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "fixed_coverage_incomplete"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-23T03:04:42Z",
      "losses": 33,
      "max_score": 55.386274611099374,
      "measured_at": null,
      "min_score": 11.59827459432436,
      "model_code_failure_rate": 0.2,
      "model_code_failures": 2,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": 0.8,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 117,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.153234157907,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": 2,
      "repaired_rate": 0.2,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 35.24218909333583,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 40
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 318,
      "canonical_public_row_identity": "publication-row.v1:intensive:mistralai-mistral-medium-3-5:58c9456c0bd2ac32",
      "capped_draws": 17,
      "codegen_cost_usd": {
        "admitted_cell_count": 4,
        "cell_count": 8,
        "cost_basis_counts": {
          "provider_reported": 14
        },
        "evidence_basis": "Provider-reported",
        "failed_cell_count": 5,
        "max": 0.3927285,
        "mean": 0.1902770625,
        "median": 0.16804049999999998,
        "min": 0.08751,
        "recorded_attempt_count": 14,
        "run_count": 9,
        "total": 1.914945
      },
      "codegen_evaluated_cells": 9,
      "conditional_success_score": 21.756661652782977,
      "contributing_entrants": null,
      "distinct_rated_opponents": 37,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": 4,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [
        "GB2-02",
        "GB2-03",
        "GB2-04",
        "GB2-08"
      ],
      "first_pass_admitted": 2,
      "first_pass_rate": 0.2222222222222222,
      "first_seen_at": null,
      "game_alias": null,
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [
        "below_generation_quality_threshold"
      ],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": 0,
      "is_recent_addition": false,
      "last_measured_at": "2026-08-05T04:22:40Z",
      "losses": 226,
      "max_score": 31.129646707507366,
      "measured_at": null,
      "min_score": 11.636247230495337,
      "model_code_failure_rate": 0.5555555555555556,
      "model_code_failures": 5,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": 0.4444444444444444,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "provisional",
      "rated_matches": 318,
      "rating_method": "sequential_elo",
      "raw_elo": 1224.5730997935657,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": 2,
      "repaired_rate": 0.2222222222222222,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "track",
      "score": 17.76423985189867,
      "score_basis": "successful-game mean adjusted by the quarter power of plugin success rate",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": null,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-20T02:25:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1984.8430422639274,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 95.06137796160141,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 160,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 30,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 14,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 160,
      "rating_method": "sequential_elo",
      "raw_elo": 1838.9026372811668,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 81.00202184525405,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 116
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1843.9420024778738,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 80.39863746617029,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-04T22:26:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1789.6986255095305,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 74.5791609476971,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-22T09:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1751.5204705553888,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 70.89182828429095,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 66
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 25,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 25,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T02:28:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1751.7035828845744,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 70.59314019339122,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 143,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 23,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 23,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-19T23:48:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 143,
      "rating_method": "sequential_elo",
      "raw_elo": 1687.8947917300393,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 65.20264997974215,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 164,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-19T23:39:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 164,
      "rating_method": "sequential_elo",
      "raw_elo": 1652.03180370545,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.721626572263794,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 98
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1644.9301421808211,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.87170060837425,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 110,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 50,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-03T14:42:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 110,
      "rating_method": "sequential_elo",
      "raw_elo": 1641.152563313432,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.28936991672205,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.0733020497882,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 15,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-03T13:20:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.1676828791458,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 57.3619117116447,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-22T14:45:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1616.069646677,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.83944130802511,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 418,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 32,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 157,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 151,
      "max_score": null,
      "measured_at": "2026-08-22T09:26:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 418,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.7594820788852,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.03900598894137,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.20594182360189764,
      "unilateral_faults": 0,
      "wins": 235
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:meta-muse-spark-1-2:8ed12b9970d2209b",
      "capped_draws": 5,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-20T02:02:55Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1582.2892427440295,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.346963426005594,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 46
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 303,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 92,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 92,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 103,
      "max_score": null,
      "measured_at": "2026-08-22T09:15:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 302,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.1126584018375,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.06934497191142,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 1,
      "wins": 107
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 100,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 47,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 46,
      "max_score": null,
      "measured_at": "2026-08-03T12:31:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 100,
      "rating_method": "sequential_elo",
      "raw_elo": 1531.0962511352168,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.32288377460864,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.001859510499461,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "capped_draws": 19,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 19,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1493.2629278529,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.19117788523471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-23T12:28:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1540.8930518724999,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.77290160209612,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 31,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 34,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.937234683748,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.41290592375142,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 20,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 20,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 40,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.4270688693366,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 37.80076732863321,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-04T23:53:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1377.7043878093432,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.14530790884301,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 136,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 24,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 48,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 78,
      "max_score": null,
      "measured_at": "2026-08-23T09:38:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 136,
      "rating_method": "sequential_elo",
      "raw_elo": 1328.9468682572074,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.004907598248348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:xiaomi-mimo-v2-5:865be584a2f7aaf7",
      "capped_draws": 41,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-07-31T00:39:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1238.9848297340284,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 17.329198413600206,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 49,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-08-23T09:56:43Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1209.1921036226092,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 15.649250107241665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:mistralai-mistral-medium-3-5:58c9456c0bd2ac32",
      "capped_draws": 17,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 51,
      "max_score": null,
      "measured_at": "2026-08-05T03:16:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1182.0336827681099,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 11.636247230495337,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-01:publication-row.v1:intensive:stepfun-step-3-7-flash:4da76a51b292ca95",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-01",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:13Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1164.068130786268,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 9.651433101795904,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 12
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-23T09:27:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1830.0318043667605,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-05T02:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1737.894247067,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 79.43336636141659,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 31,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-05T01:25:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1707.3717186637177,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.77270456368558,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 37
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 35,
      "draws": 30,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-04T08:44:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1694.6686240486547,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.36660657293471,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 29.98404749947013,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 68,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-23T09:27:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1601.5705707988113,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.06793491447559,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T02:22:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.1507466448422,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.85138391276626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 28,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 14,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-23T14:10:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 28,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.1315475505453,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.26149604339514,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 85.34944487358055,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 98,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-15T01:45:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 98,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.1681603311224,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.25129104934696,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 6.501890762960602,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 58,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-08-22T08:14:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1502.869141070355,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.812606919993172,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 5
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-03T10:38:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1497.0520433424101,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.79810278001538,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 60,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:xiaomi-mimo-v2-5:865be584a2f7aaf7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-31T01:21:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 60,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.1338632198867,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.338864125825364,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.268439966447993,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 106,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-15T01:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.5010269282043,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 23.78419992194771,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-23T05:29:53Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1521.1352852847508,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.752949450340513,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 109,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1461.0862907777541,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.20918702880969,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-03T08:04:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1472.2427790750996,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.976294071045,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 114,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 56,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-04T08:44:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 114,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.6046613504113,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.686387180079826,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.910536671832062,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-23T06:52:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1465.5824743341007,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 18.648854275319852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:openai-gpt-oss-120b:707f3723f9845847",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 31,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 10,
      "max_score": null,
      "measured_at": "2026-08-03T14:23:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.1637680119986,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 13.814065400064843,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 56,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 26,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-04T05:07:08Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1448.1010532318462,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 13.456150792860978,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 2,
      "wins": 1
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 122,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-19T22:29:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 122,
      "rating_method": "sequential_elo",
      "raw_elo": 1428.5395963112296,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 13.078411737521655,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.3334817333716131,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-02:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 15,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-02",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1482.8561157275458,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 11.59827459432436,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-21T15:52:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1873.3759975611176,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 84
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-03T14:17:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1837.3301063724912,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 92.59586913113255,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 29.182495748947275,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-22T17:46:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.8727510068502,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 86.9870467732465,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 20,
      "draws": 22,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-03T06:16:26Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1659.0010157114255,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.5967962093199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 27.678571428571434,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 21,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-03T14:16:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1599.7752708410653,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.693530462272456,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 32.49928516630233,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 41,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-21T05:32:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.2383618839162,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.06942397101405,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 250,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 8,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 92,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 92,
      "max_score": null,
      "measured_at": "2026-08-22T20:25:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 250,
      "rating_method": "sequential_elo",
      "raw_elo": 1543.8864018616787,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 54.3795837338173,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.042462425705284,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 238,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:z-ai-glm-5-2:bc1714da76816a46",
      "capped_draws": 18,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 84,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "z-ai/glm-5.2",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GLM-5.2",
      "model_slug": "z-ai-glm-5-2",
      "plugin_success_rate": null,
      "provider": "Zhipu",
      "provider_key": "z-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 238,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.306297413937,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "z-ai",
        "provider_model": "z-ai/glm-5.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_7fad32_to_brackets_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.3313100517875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 1.9042490427370184,
      "unilateral_faults": 0,
      "wins": 95
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:meta-muse-spark-1-2:8ed12b9970d2209b",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 14,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "meta/muse-spark-1.2",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-21T11:42:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Muse Spark 1.2",
      "model_slug": "meta-muse-spark-1-2",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.6439862621312,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "meta/muse-spark-1.2",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.63977924133589,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 69,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 24,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-08-03T14:17:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1523.1530595800598,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.69220134120665,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-03T12:18:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1503.0287857501219,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.64591903633767,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 4,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-22T14:35:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1544.6816547576702,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.57541663713608,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-22T12:02:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.74320418467,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.671930557268624,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 19
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-22T21:12:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1520.056619582484,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.74500116475145,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 62,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 53,
      "max_score": null,
      "measured_at": "2026-08-22T23:22:46Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.3749817413207,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.0930986190164,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 118,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 6,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 48,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-23T03:05:15Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 118,
      "rating_method": "sequential_elo",
      "raw_elo": 1454.1101031373976,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.56882637540658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 2.084924851410568,
      "unilateral_faults": 0,
      "wins": 29
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 112,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 33,
      "max_score": null,
      "measured_at": "2026-08-22T13:52:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 112,
      "rating_method": "sequential_elo",
      "raw_elo": 1438.3742508178495,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.21229308756867,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 3.286043419179858,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 128,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 46,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-22T21:12:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 128,
      "rating_method": "sequential_elo",
      "raw_elo": 1435.5845812595855,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.158820258821116,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 138,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 9,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 39,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-21T05:32:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 138,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.9524119202586,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.11059502696876,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 93,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 4,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 27,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-21T11:43:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 93,
      "rating_method": "sequential_elo",
      "raw_elo": 1439.6598711541665,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.881693886910185,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.821062312939668,
      "unilateral_faults": 0,
      "wins": 36
    },
    {
      "admitted_plugins": 5,
      "attempted_matches": 39,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 18,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-23T15:12:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 35,
      "rating_method": "sequential_elo",
      "raw_elo": 1508.2407303398938,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.512996050435966,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 96.61669937087152,
      "unilateral_faults": 4,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 55,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-03:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 3,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 25,
      "draws": 18,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-03",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-03T03:06:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 54,
      "rating_method": "sequential_elo",
      "raw_elo": 1433.9628765018,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.28813655813136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 23.66998624632421,
      "unilateral_faults": 1,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 5,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1867.362240038843,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-22T05:58:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1813.5063596110099,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 91.32241413921264,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 140,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 60,
      "draws": 21,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T04:13:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 140,
      "rating_method": "sequential_elo",
      "raw_elo": 1756.1344548669742,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 82.0434973958146,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 15.606750070474945,
      "unilateral_faults": 0,
      "wins": 102
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 144,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 47,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-22T06:50:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 144,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.845435170706,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 80.95493130171027,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 82
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-05T01:54:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1623.7791355637896,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.996358539488305,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 289,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 107,
      "draws": 74,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 83,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 286,
      "rating_method": "sequential_elo",
      "raw_elo": 1597.9332057560987,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.70973443654603,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 85,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-22T04:12:35Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1605.7836316615358,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.29009953663199,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 40,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-22T06:51:00Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1605.3952927027833,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.87607730332684,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 40,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.6914890100186,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.06108211106203,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 11,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-23T12:51:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1595.3194324712535,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.942602650877994,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 9,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-22T17:44:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1563.2617872617693,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.88860616405384,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-23T12:27:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1547.063493316194,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.953702406627194,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 22
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 126,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 49,
      "draws": 81,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 126,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.354766936686,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.149311285803776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.617825470805693,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 58,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:xiaomi-mimo-v2-5:865be584a2f7aaf7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 29,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-07-31T02:31:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 58,
      "rating_method": "sequential_elo",
      "raw_elo": 1494.504648883028,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.772376702118756,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 21.344455490411935,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-1-flash-lite:ff56b3b6c0d25588",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 54,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1484.7935464109898,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 40.36325367187167,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:41Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1479.6409821341078,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 39.474444158374034,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:openai-gpt-oss-120b:707f3723f9845847",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 32,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:31Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1478.284379118747,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.75509843220986,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 52,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T05:05:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1474.3430744138302,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 38.653128654939394,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 257,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 99,
      "draws": 163,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 59,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 256,
      "rating_method": "sequential_elo",
      "raw_elo": 1451.4196953279754,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 36.70643364563969,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.27254531628119416,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 56,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 16,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1455.207397477533,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.776619836599615,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 151,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 56,
      "draws": 79,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-22T04:11:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 151,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.440206836578,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.58935434104422,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 29,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 32,
      "max_score": null,
      "measured_at": "2026-08-05T05:04:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1447.491289436351,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.75060930600307,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 146,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 52,
      "max_score": null,
      "measured_at": "2026-08-23T02:43:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 146,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.5035179780361,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.41381726074275,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 35
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 49,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T05:11:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1431.281453340056,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.883837501980675,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 7
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 43,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 27,
      "max_score": null,
      "measured_at": "2026-08-04T23:00:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1426.7745846890361,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.278757459984458,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-04:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 44,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-04",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1421.735317704969,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.587564175213476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-22T08:04:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 2001.572693385237,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 94.27284751416232,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 93
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 12,
      "max_score": null,
      "measured_at": "2026-08-05T00:52:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1984.5756471110153,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 92.46710125142182,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 68
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 274,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 104,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 274,
      "rating_method": "sequential_elo",
      "raw_elo": 1928.0234348943654,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 88.3817448074802,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 235
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 120,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-03T14:57:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 120,
      "rating_method": "sequential_elo",
      "raw_elo": 1935.02209164043,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 87.48023052744581,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 20.294267162641567,
      "unilateral_faults": 0,
      "wins": 100
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-05T01:40:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1921.1578815317785,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 86.85420097557086,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-05T01:40:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1811.7287474218497,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 77.21666620850746,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 134,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 52,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-22T10:31:06Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 134,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.3881365012405,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 76.16684999097536,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 97
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-15T00:19:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1659.9607128670973,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.917443301992066,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 65
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-04T22:34:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1661.7384364801353,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 63.893829202898324,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-04T23:23:49Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1642.8634951956521,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 62.12239074156852,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 41
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-03T08:44:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.2220406835493,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.334280478082064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 39
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-23T07:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1596.0023160248443,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.37713182359818,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-03T12:11:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1559.729054266692,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.0033758790599,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 47
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 610,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 220,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 275,
      "max_score": null,
      "measured_at": "2026-08-23T13:45:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 610,
      "rating_method": "sequential_elo",
      "raw_elo": 1537.2233988941953,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.94753611433414,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 335
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 48,
      "max_score": null,
      "measured_at": "2026-08-03T10:18:45Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1546.2909017340082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.89836516661261,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 42
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 108,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 54,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-03T14:57:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 108,
      "rating_method": "sequential_elo",
      "raw_elo": 1539.312046490709,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 53.60093706896381,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 4.1413142610575715,
      "unilateral_faults": 0,
      "wins": 53
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.691509009023,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.77369810249913,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 192,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 82,
      "max_score": null,
      "measured_at": "2026-08-20T05:43:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 192,
      "rating_method": "sequential_elo",
      "raw_elo": 1514.867968636721,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.28009274749246,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 110
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-23T14:10:47Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1571.444849455973,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.24945473815348,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 22,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 11,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-22T11:34:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 22,
      "rating_method": "sequential_elo",
      "raw_elo": 1532.722998103657,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.02675226585254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 60.5072070285374,
      "unilateral_faults": 0,
      "wins": 13
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 188,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 91,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 101,
      "max_score": null,
      "measured_at": "2026-08-05T00:09:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 188,
      "rating_method": "sequential_elo",
      "raw_elo": 1457.9789820510734,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.15142583047198,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.686045325052198,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-20T12:56:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.4912588279985,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.65403638689062,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 9
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:stepfun-step-3-7-flash:4da76a51b292ca95",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 45,
      "max_score": null,
      "measured_at": "2026-08-03T10:09:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1420.039006789118,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 42.840832148787285,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 51
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 296,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 218,
      "max_score": null,
      "measured_at": "2026-08-22T23:45:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 296,
      "rating_method": "sequential_elo",
      "raw_elo": 1223.5192759386232,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.141806979414127,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:mistralai-mistral-medium-3-5:58c9456c0bd2ac32",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-08-05T01:39:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1215.6711985096656,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.36438641581923,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:google-gemini-3-1-flash-lite:ff56b3b6c0d25588",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-08-05T00:53:07Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1174.3948018938386,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.711146730771695,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 16
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 312,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-05:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 108,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-05",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 242,
      "max_score": null,
      "measured_at": "2026-08-22T23:41:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 312,
      "rating_method": "sequential_elo",
      "raw_elo": 1156.0898611341393,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 20.247158692047016,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-21T05:32:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 2004.117017853337,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 93.18006300131891,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 83
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-23T03:04:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1975.6465528059348,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 91.56194509481253,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 248
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-20T17:51:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1956.1813224870132,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 89.25646806706095,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-05T00:01:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1929.4026084325167,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 86.36800772140613,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 57
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 9,
      "max_score": null,
      "measured_at": "2026-08-22T20:09:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 89,
      "rating_method": "sequential_elo",
      "raw_elo": 1884.4844196491322,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 83.09168848413222,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.954627669472988,
      "unilateral_faults": 0,
      "wins": 72
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 33,
      "draws": 3,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 11,
      "max_score": null,
      "measured_at": "2026-08-03T14:42:32Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 1884.0000254094712,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 82.54672029424074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 54
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 66,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-03T12:25:28Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 66,
      "rating_method": "sequential_elo",
      "raw_elo": 1864.5341381574124,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 80.84833683146083,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 17.33472217815261,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 62,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 30,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-03T10:32:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 62,
      "rating_method": "sequential_elo",
      "raw_elo": 1849.5527583256137,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 79.45887582150341,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 19.244078834871203,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 24,
      "max_score": null,
      "measured_at": "2026-08-05T00:01:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1782.5107591539809,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 74.17041747029772,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 50
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-08-03T13:30:44Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1705.0975680441916,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.70578978678658,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 44
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 74,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:openai-gpt-oss-120b:707f3723f9845847",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 36,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-03T11:32:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 74,
      "rating_method": "sequential_elo",
      "raw_elo": 1701.327703247478,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 67.33768307109139,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.985026918962571,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 60,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-20T18:12:10Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.4547207601838,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.91814020044125,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 53,
      "draws": 8,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-22T13:31:37Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1606.375142289731,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.52933478522943,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 78
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 64,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:xiaomi-mimo-v2-5:865be584a2f7aaf7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 26,
      "max_score": null,
      "measured_at": "2026-07-31T20:22:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 64,
      "rating_method": "sequential_elo",
      "raw_elo": 1600.8399247445086,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 58.591838652401584,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 18.26736729460423,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 174,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 75,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 174,
      "rating_method": "sequential_elo",
      "raw_elo": 1552.1910999620195,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 56.128166821353254,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 2,
      "max_score": null,
      "measured_at": "2026-08-22T19:42:16Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1610.153408293399,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 55.386274611099374,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 14
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 8,
      "max_score": null,
      "measured_at": "2026-08-23T12:25:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.0114222032025,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 52.06957808560736,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 28
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 583,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 201,
      "draws": 17,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 280,
      "max_score": null,
      "measured_at": "2026-08-23T04:58:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 583,
      "rating_method": "sequential_elo",
      "raw_elo": 1496.398635934153,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.19784527381407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 286
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 15,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-22T16:31:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 15,
      "rating_method": "sequential_elo",
      "raw_elo": 1524.5925491348792,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.93379015513136,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 81.25,
      "unilateral_faults": 0,
      "wins": 8
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 288,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 103,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 147,
      "max_score": null,
      "measured_at": "2026-08-23T00:33:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 288,
      "rating_method": "sequential_elo",
      "raw_elo": 1446.4894914486981,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.980742920105875,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 129
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:stepfun-step-3-7-flash:4da76a51b292ca95",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-05T00:01:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1450.1280740563188,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.55383945263552,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 38
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 104,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-08-04T23:08:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 104,
      "rating_method": "sequential_elo",
      "raw_elo": 1412.3428545385407,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.617353114418286,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.045003647426665,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 81,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 6,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-04T23:17:48Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 81,
      "rating_method": "sequential_elo",
      "raw_elo": 1413.606033323522,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 43.29134777487506,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.465763037423269,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 5,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1292.2789954568457,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.30669861449365,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 83,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:google-gemini-3-1-flash-lite:ff56b3b6c0d25588",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:51Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 83,
      "rating_method": "sequential_elo",
      "raw_elo": 1285.0945886378513,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.519767162748906,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 10.804472558998102,
      "unilateral_faults": 0,
      "wins": 27
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 72,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 34,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 50,
      "max_score": null,
      "measured_at": "2026-08-05T00:53:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 72,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.7125698415605,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.46308983512399,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 14.770573598065289,
      "unilateral_faults": 0,
      "wins": 21
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:mistralai-mistral-medium-3-5:58c9456c0bd2ac32",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-08-05T02:35:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1269.3787546862945,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 31.129646707507366,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 26
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-06:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-06",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 55,
      "max_score": null,
      "measured_at": "2026-08-05T00:52:58Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1257.9871534436184,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 30.12382384874148,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 23
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 68,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 32,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-05T04:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 68,
      "rating_method": "sequential_elo",
      "raw_elo": 2007.7650814322424,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 16.4429265428846,
      "unilateral_faults": 0,
      "wins": 67
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-23T08:55:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1985.9471428986744,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 98.38140095757626,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 6,
      "max_score": null,
      "measured_at": "2026-08-05T04:35:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1943.974131521536,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 93.82012264656494,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 76
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-19T21:21:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1908.5825702078523,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 90.48850476973648,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 89
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T03:23:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1790.5232339769955,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 77.77956211899175,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 61
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 40,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 21,
      "max_score": null,
      "measured_at": "2026-08-05T01:18:27Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1776.5903445158342,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 76.39149789263541,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 59
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1759.9984530561082,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 74.93025959728134,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-05T02:43:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1741.7863118703656,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.77919861333487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 25,
      "max_score": null,
      "measured_at": "2026-08-04T20:07:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1737.270344317228,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.31048780319064,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 55
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-22T23:00:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1734.1032480369697,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.2896551782984,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 70
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 20,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 0,
      "max_score": null,
      "measured_at": "2026-08-22T06:40:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 20,
      "rating_method": "sequential_elo",
      "raw_elo": 1745.028439951044,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 68.66906686669674,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 65.3589451179962,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 57,
      "max_score": null,
      "measured_at": "2026-08-23T02:23:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.7238466980018,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 65.68620340611055,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 101
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 78,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-04T22:51:36Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 78,
      "rating_method": "sequential_elo",
      "raw_elo": 1660.8923428169323,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 64.32521389783669,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.5043950463012,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 43,
      "max_score": null,
      "measured_at": "2026-08-04T21:03:19Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1629.281190088032,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 61.26423443502467,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:moonshotai-kimi-k3:6cfd7a6936cf4591",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "moonshotai/kimi-k3",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-19T21:33:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Kimi K3",
      "model_slug": "moonshotai-kimi-k3",
      "plugin_success_rate": null,
      "provider": "Moonshot",
      "provider_key": "moonshotai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1608.0632436917545,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "moonshotai",
        "provider_model": "moonshotai/kimi-k3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 60.356605978893036,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 108
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 38,
      "max_score": null,
      "measured_at": "2026-08-03T15:11:05Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1609.3281773288047,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.19331770120144,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 48
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 57,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 72,
      "max_score": null,
      "measured_at": "2026-08-19T21:21:59Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1505.6448959972681,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 49.63125807718102,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 90
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 154,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 55,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-22T19:11:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 154,
      "rating_method": "sequential_elo",
      "raw_elo": 1500.2174214587583,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.9850812289486,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 48,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 24,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-23T14:09:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 48,
      "rating_method": "sequential_elo",
      "raw_elo": 1557.9397208469782,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 48.24161735863407,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 4,
      "attempted_matches": 608,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 4,
      "distinct_rated_opponents": 221,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 326,
      "max_score": null,
      "measured_at": "2026-08-23T05:21:30Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 608,
      "rating_method": "sequential_elo",
      "raw_elo": 1481.5992503742432,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 47.0302536987219,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 282
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 303,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 110,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 154,
      "max_score": null,
      "measured_at": "2026-08-23T08:13:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 303,
      "rating_method": "sequential_elo",
      "raw_elo": 1480.0791092283798,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.86769680909644,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 149
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 96,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:google-gemini-3-1-flash-lite:ff56b3b6c0d25588",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 62,
      "max_score": null,
      "measured_at": "2026-08-05T02:09:18Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 96,
      "rating_method": "sequential_elo",
      "raw_elo": 1483.6954722538387,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 46.38961044453501,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.017308256680951,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:openai-gpt-oss-120b:707f3723f9845847",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 54,
      "max_score": null,
      "measured_at": "2026-08-05T01:17:39Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1441.4354314549128,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.715724086496124,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 30
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 89,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:stepfun-step-3-7-flash:4da76a51b292ca95",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-05T03:50:20Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 89,
      "rating_method": "sequential_elo",
      "raw_elo": 1352.721001533367,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.63495353216882,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.954627669472988,
      "unilateral_faults": 0,
      "wins": 33
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 44,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 58,
      "max_score": null,
      "measured_at": "2026-08-05T04:12:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1300.3603544346433,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.27162069011934,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 34
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 166,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 62,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 121,
      "max_score": null,
      "measured_at": "2026-08-22T06:50:33Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 166,
      "rating_method": "sequential_elo",
      "raw_elo": 1275.4800377038869,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 25.78170138825857,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 45
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 16,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 9,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 15,
      "max_score": null,
      "measured_at": "2026-08-19T21:57:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 16,
      "rating_method": "sequential_elo",
      "raw_elo": 1305.0776107344343,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 21.997140822640443,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 77.5178125181665,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 84,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-07:publication-row.v1:intensive:mistralai-mistral-medium-3-5:58c9456c0bd2ac32",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "mistralai/mistral-medium-3-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-07",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 64,
      "max_score": null,
      "measured_at": "2026-08-05T04:22:40Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Mistral Medium 3.5",
      "model_slug": "mistralai-mistral-medium-3-5",
      "plugin_success_rate": null,
      "provider": "Mistral",
      "provider_key": "mistral",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 84,
      "rating_method": "sequential_elo",
      "raw_elo": 1231.208763210193,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "mistral",
        "provider_model": "mistralai/mistral-medium-3-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 19.89636625730998,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 10.482614454664043,
      "unilateral_faults": 0,
      "wins": 20
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-fable-5:5a1cc0fafbb266c7",
      "capped_draws": 1,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 1,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-fable-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-05T04:44:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Fable 5",
      "model_slug": "claude-fable-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 2039.7954541913955,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-fable-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 100.0,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 87
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:x-ai-grok-4-5:b0a92c183e177d45",
      "capped_draws": 2,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 64,
      "draws": 2,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "x-ai/grok-4.5",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 20,
      "max_score": null,
      "measured_at": "2026-08-22T17:44:01Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Grok 4.5",
      "model_slug": "x-ai-grok-4-5",
      "plugin_success_rate": null,
      "provider": "xAI",
      "provider_key": "x-ai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1945.9379565959005,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "x-ai",
        "provider_model": "x-ai/grok-4.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 91.324739517719,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 148
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 90,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-sonnet-5:4c96a5e86d12d58b",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-sonnet-5",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 13,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Sonnet 5",
      "model_slug": "claude-sonnet-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 90,
      "rating_method": "sequential_elo",
      "raw_elo": 1883.2982680044097,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-sonnet-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 83.58905380078096,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.664241836095918,
      "unilateral_faults": 0,
      "wins": 77
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-sol:c051d828081d0d91",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-sol",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Sol",
      "model_slug": "gpt-5-6-sol",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1857.759542012682,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-sol",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 80.96609226971566,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 75
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-5:eb9fefeb3ace38a1",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T03:02:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.5",
      "model_slug": "gpt-5-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1788.7771703951637,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 73.75320729186035,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 58
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 158,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-opus-5:9f8812658c6b6343",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 69,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-5",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 39,
      "max_score": null,
      "measured_at": "2026-08-05T04:44:12Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 5",
      "model_slug": "claude-opus-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 158,
      "rating_method": "sequential_elo",
      "raw_elo": 1777.792006324548,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "54d76675b207eebe45a76f6fc3a23b868c53219a3b71f22bb7492e195b61544d",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 72.26518773471317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 12.154975300928378,
      "unilateral_faults": 0,
      "wins": 119
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-opus-4-8:ebbf2432c9a71c0d",
      "capped_draws": 0,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 41,
      "draws": 0,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-8",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-05T02:16:17Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.8",
      "model_slug": "claude-opus-4-8",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1756.3114534666295,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-8",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 70.21149192288846,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 63
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-4:6f2d7de576c6f541",
      "capped_draws": 11,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 11,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.4",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 23,
      "max_score": null,
      "measured_at": "2026-08-15T02:22:24Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.4",
      "model_slug": "gpt-5-4",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1649.4348299353023,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.4",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 59.03633551296827,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 52
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-terra:8869a1009cce8005",
      "capped_draws": 13,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 13,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-terra",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 30,
      "max_score": null,
      "measured_at": "2026-08-04T22:26:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Terra",
      "model_slug": "gpt-5-6-terra",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1577.3366324646952,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-terra",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 51.49765579998893,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 43
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 298,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-6-flash:1efb2291cbf800fd",
      "capped_draws": 97,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 116,
      "draws": 97,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.6-flash",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 86,
      "max_score": null,
      "measured_at": "2026-08-22T23:22:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.6 Flash",
      "model_slug": "google-gemini-3-6-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 298,
      "rating_method": "sequential_elo",
      "raw_elo": 1561.6648885423429,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.6-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 50.92804253858354,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 115
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 454,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:o3:908e4e2cf254357c",
      "capped_draws": 187,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 176,
      "draws": 187,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "o3",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 137,
      "max_score": null,
      "measured_at": "2026-08-22T14:19:03Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "O3",
      "model_slug": "o3",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 454,
      "rating_method": "sequential_elo",
      "raw_elo": 1507.7257361361333,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "o3",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "9509d997c322d464abce97a91e4e9fd7e30ea9d0340e76e3198c634a0c7e5999",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 45.3120429850668,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 130
    },
    {
      "admitted_plugins": 3,
      "attempted_matches": 42,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:stealth-ox-alpha:650c74dfce556ee1",
      "capped_draws": 10,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 3,
      "distinct_rated_opponents": 21,
      "draws": 10,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stealth/ox-alpha",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 7,
      "max_score": null,
      "measured_at": "2026-08-23T14:12:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Ox Alpha",
      "model_slug": "stealth-ox-alpha",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 42,
      "rating_method": "sequential_elo",
      "raw_elo": 1570.5181600374551,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "stealth/ox-alpha",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 44.46972348405135,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 85.34944487358057,
      "unilateral_faults": 0,
      "wins": 25
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 94,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:tencent-hy3-preview:cbb13c5a7417a861",
      "capped_draws": 26,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 26,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "tencent/hy3-preview",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 37,
      "max_score": null,
      "measured_at": "2026-08-03T12:45:25Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Hy3 Preview",
      "model_slug": "tencent-hy3-preview",
      "plugin_success_rate": null,
      "provider": "Tencent",
      "provider_key": "tencent",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 94,
      "rating_method": "sequential_elo",
      "raw_elo": 1476.1794699081136,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "tencent",
        "provider_model": "tencent/hy3-preview",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 41.11348750799539,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 7.54891760425771,
      "unilateral_faults": 0,
      "wins": 31
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 102,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5:c96e6073f5cb5c2e",
      "capped_draws": 59,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 51,
      "draws": 59,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 28,
      "max_score": null,
      "measured_at": "2026-08-04T23:45:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT 5",
      "model_slug": "gpt-5",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 102,
      "rating_method": "sequential_elo",
      "raw_elo": 1425.1578264572643,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 35.948611997746326,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 5.516463908214657,
      "unilateral_faults": 0,
      "wins": 15
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 17,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:thinkingmachines-inkling-small:bbca5c562fb1ab46",
      "capped_draws": 16,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 16,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling-small",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 1,
      "max_score": null,
      "measured_at": "2026-08-22T23:00:21Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling Small",
      "model_slug": "thinkingmachines-inkling-small",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 17,
      "rating_method": "sequential_elo",
      "raw_elo": 1468.5508035025312,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling-small",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 34.74879684007773,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 74.10113019775793,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 82,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:openai-gpt-oss-120b:707f3723f9845847",
      "capped_draws": 61,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 39,
      "draws": 61,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "openai/gpt-oss-120b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 18,
      "max_score": null,
      "measured_at": "2026-08-05T02:53:14Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-OSS 120B",
      "model_slug": "openai-gpt-oss-120b",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 82,
      "rating_method": "sequential_elo",
      "raw_elo": 1409.8830365675533,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "openai/gpt-oss-120b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.88171545537361,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.132129994845172,
      "unilateral_faults": 0,
      "wins": 3
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 172,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:nvidia-nemotron-3-ultra-550b-a55b:671e21a17463ea94",
      "capped_draws": 120,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 2,
      "distinct_rated_opponents": 83,
      "draws": 120,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 41,
      "max_score": null,
      "measured_at": "2026-08-05T04:29:22Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Nemotron 3 Ultra 550B A55B",
      "model_slug": "nvidia-nemotron-3-ultra-550b-a55b",
      "plugin_success_rate": null,
      "provider": "NVIDIA",
      "provider_key": "nvidia",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 172,
      "rating_method": "sequential_elo",
      "raw_elo": 1408.5749166804935,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "nvidia",
        "provider_model": "nvidia/nemotron-3-ultra-550b-a55b",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.843689445221074,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.951570146038407,
      "unilateral_faults": 0,
      "wins": 11
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:deepseek-deepseek-v4-flash:3321a752a2ed6366",
      "capped_draws": 69,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 46,
      "draws": 69,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T04:43:54Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Flash",
      "model_slug": "deepseek-deepseek-v4-flash",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1406.790186771671,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.8121598719359,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 1
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 18,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:qwen-qwen3-8-max:83f392701e202fd4",
      "capped_draws": 12,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 8,
      "draws": 12,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "qwen/qwen3.8-max",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 4,
      "max_score": null,
      "measured_at": "2026-08-23T02:42:56Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Qwen3.8 Max",
      "model_slug": "qwen-qwen3-8-max",
      "plugin_success_rate": null,
      "provider": "Alibaba",
      "provider_key": "qwen",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 18,
      "rating_method": "sequential_elo",
      "raw_elo": 1453.3660051372515,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "qwen",
        "provider_model": "qwen/qwen3.8-max",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.42398580815915,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 70.95786693528086,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 70,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:xiaomi-mimo-v2-5:865be584a2f7aaf7",
      "capped_draws": 65,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 35,
      "draws": 65,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "xiaomi/mimo-v2.5",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 3,
      "max_score": null,
      "measured_at": "2026-07-31T02:38:23Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "MiMo-V2.5",
      "model_slug": "xiaomi-mimo-v2-5",
      "plugin_success_rate": null,
      "provider": "Xiaomi",
      "provider_key": "xiaomi",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 70,
      "rating_method": "sequential_elo",
      "raw_elo": 1405.564866061363,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "xiaomi",
        "provider_model": "xiaomi/mimo-v2.5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": false,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_pre_845b695_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 33.05738226960813,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 15.58908290969266,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 76,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:deepseek-deepseek-v4-pro:bda2de12b3bef61c",
      "capped_draws": 55,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 37,
      "draws": 55,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "deepseek/deepseek-v4-pro",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 19,
      "max_score": null,
      "measured_at": "2026-08-04T09:10:50Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "DeepSeek V4 Pro",
      "model_slug": "deepseek-deepseek-v4-pro",
      "plugin_success_rate": null,
      "provider": "DeepSeek",
      "provider_key": "deepseek",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 76,
      "rating_method": "sequential_elo",
      "raw_elo": 1402.9553709497593,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "deepseek",
        "provider_model": "deepseek/deepseek-v4-pro",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.98184099437737,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 13.230288229818967,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 92,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-1-flash-lite:ff56b3b6c0d25588",
      "capped_draws": 66,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 45,
      "draws": 66,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.1-flash-lite",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 22,
      "max_score": null,
      "measured_at": "2026-08-05T02:15:42Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.1 Flash Lite",
      "model_slug": "google-gemini-3-1-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 92,
      "rating_method": "sequential_elo",
      "raw_elo": 1391.2575126535978,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.1-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.18804360592281,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 8.09758473652126,
      "unilateral_faults": 0,
      "wins": 4
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 80,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:stepfun-step-3-7-flash:4da76a51b292ca95",
      "capped_draws": 63,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 38,
      "draws": 63,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "stepfun/step-3.7-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 17,
      "max_score": null,
      "measured_at": "2026-08-05T00:38:29Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Step 3.7 Flash",
      "model_slug": "stepfun-step-3-7-flash",
      "plugin_success_rate": null,
      "provider": "StepFun",
      "provider_key": "stepfun",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 80,
      "rating_method": "sequential_elo",
      "raw_elo": 1392.660028685881,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "stepfun",
        "provider_model": "stepfun/step-3.7-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 32.024524339620434,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 11.805555555555554,
      "unilateral_faults": 0,
      "wins": 0
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 178,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:claude-opus-4-5:0dacb4d5b9cf9367",
      "capped_draws": 93,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 61,
      "draws": 93,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "anthropic",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "claude-opus-4-5",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 68,
      "max_score": null,
      "measured_at": "2026-08-21T15:41:34Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Claude Opus 4.5",
      "model_slug": "claude-opus-4-5",
      "plugin_success_rate": null,
      "provider": "Anthropic",
      "provider_key": "anthropic",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 178,
      "rating_method": "sequential_elo",
      "raw_elo": 1342.9635954463263,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High effort + 32,000 thinking tokens",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "anthropic",
        "provider_model": "claude-opus-4-5",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "anthropic",
        "provider_setting_label": "High effort + 32,000 thinking tokens",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High effort + 32,000 thinking tokens",
        "reasoning_catalog_sha256": "3c336499ab8e8904e188765629ffba06ae79f65152b658d8375c55b79dea9425",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 28.34925891692476,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 17
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 170,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:thinkingmachines-inkling:8db7573c02acc990",
      "capped_draws": 101,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 63,
      "draws": 101,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "max",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "thinkingmachines/inkling",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 67,
      "max_score": null,
      "measured_at": "2026-08-21T19:14:04Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Inkling",
      "model_slug": "thinkingmachines-inkling",
      "plugin_success_rate": null,
      "provider": "Other",
      "provider_key": "other",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 170,
      "rating_method": "sequential_elo",
      "raw_elo": 1339.095194087079,
      "reasoning_bracket": "intensive",
      "reasoning_level": "Max",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "other",
        "provider_model": "thinkingmachines/inkling",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "max",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "Max",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "Max",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "max"
      },
      "reasoning_setting": "max",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 27.872484354770776,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 2,
      "attempted_matches": 162,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-5-flash-lite:abb2b9fa09f58cba",
      "capped_draws": 100,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 58,
      "draws": 100,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash-lite",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 56,
      "max_score": null,
      "measured_at": "2026-08-21T18:21:11Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash Lite",
      "model_slug": "google-gemini-3-5-flash-lite",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 162,
      "rating_method": "sequential_elo",
      "raw_elo": 1329.9225797807596,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash-lite",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "d44bd3ed45106a316bc5187d913b92f471a2b698ae22aa9dee8e13db395d4063",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 26.835835838194487,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 0.0,
      "unilateral_faults": 0,
      "wins": 6
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 88,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:gpt-5-6-luna:0e3f3e6646cbf8db",
      "capped_draws": 51,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 42,
      "draws": 51,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openai",
        "effective_request_value": "xhigh",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "gpt-5.6-luna",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 35,
      "max_score": null,
      "measured_at": "2026-08-21T18:10:38Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "GPT-5.6 Luna",
      "model_slug": "gpt-5-6-luna",
      "plugin_success_rate": null,
      "provider": "OpenAI",
      "provider_key": "openai",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 88,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.0394459572435,
      "reasoning_bracket": "intensive",
      "reasoning_level": "XHigh",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "openai",
        "provider_model": "gpt-5.6-luna",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_exact",
          "request_mode": "effort",
          "requested_effort": "xhigh",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openai",
        "provider_setting_label": "XHigh",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "XHigh",
        "reasoning_catalog_sha256": "e5302719c34b1add00008c28b130eab2c2e65206b2221d52129056bbf928634c",
        "reasoning_policy_version": "gb2_reasoning_brackets_v2",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "xhigh"
      },
      "reasoning_setting": "xhigh",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.22675683362329,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.249894000318006,
      "unilateral_faults": 0,
      "wins": 2
    },
    {
      "admitted_plugins": 1,
      "attempted_matches": 86,
      "canonical_public_row_identity": "publication-game-row.v1:GB2-08:publication-row.v1:intensive:google-gemini-3-5-flash:8820630a07e04d7e",
      "capped_draws": 57,
      "codegen_cost_usd": null,
      "codegen_evaluated_cells": null,
      "conditional_success_score": null,
      "contributing_entrants": 1,
      "distinct_rated_opponents": 43,
      "draws": 57,
      "eligibility_flag": false,
      "entry_count": null,
      "evaluated_setting_identity": {
        "canonical_provider_route": "openrouter",
        "effective_request_value": "high",
        "output_mode": "unknown_legacy",
        "prompt_identity": "unknown_legacy",
        "prompt_profile_identity": "unknown_legacy",
        "provider_model": "google/gemini-3.5-flash",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "request_mode": "effort",
        "resolution_status": "opaque_historical",
        "schema_version": "evaluated_setting_identity.v1"
      },
      "failed_game_aliases": [],
      "first_pass_admitted": null,
      "first_pass_rate": null,
      "first_seen_at": null,
      "game_alias": "GB2-08",
      "generation_policy": {
        "generation_policy": "quality_generation_policy",
        "stream_idle_timeout_seconds": null,
        "streaming_enabled": null,
        "strict_wall_clock_timeout_seconds": null,
        "timeout_mode": "provider_route_timeout_guard"
      },
      "generation_timing": {
        "finish_reason": "unknown_legacy",
        "first_progress_after_seconds": null,
        "generation_completed_at": null,
        "generation_started_at": null,
        "generation_wall_clock_seconds": null,
        "stream_progress_event_count": null
      },
      "ineligibility_reason_codes": [],
      "infra_excluded_game_aliases": [],
      "infra_failures_excluded": null,
      "is_recent_addition": false,
      "last_measured_at": null,
      "losses": 29,
      "max_score": null,
      "measured_at": "2026-08-05T03:58:52Z",
      "min_score": null,
      "model_code_failure_rate": null,
      "model_code_failures": null,
      "model_display_name": "Gemini 3.5 Flash",
      "model_slug": "google-gemini-3-5-flash",
      "plugin_success_rate": null,
      "provider": "Google",
      "provider_key": "google",
      "rank": null,
      "rank_movement": null,
      "rank_movement_baseline_at": null,
      "ranking_status": "not_applicable",
      "rated_matches": 86,
      "rating_method": "sequential_elo",
      "raw_elo": 1316.0263767118158,
      "reasoning_bracket": "intensive",
      "reasoning_level": "High",
      "reasoning_provenance": {
        "code_output_mode": "unknown_legacy",
        "code_prompt_version": "unknown_legacy",
        "generation_settings_public": {
          "max_tokens": null,
          "stream": null,
          "temperature": null
        },
        "prompt_identity": "unknown_legacy",
        "prompt_profile": "unknown_legacy",
        "provider": "google",
        "provider_model": "google/gemini-3.5-flash",
        "provider_reasoning_params": {
          "bracket": "intensive",
          "bracket_eligible": true,
          "evidence_status": "retained_literal_legacy",
          "request_mode": "effort",
          "requested_effort": "high",
          "source": "retained_generation_evidence",
          "track_id": "full_freedom/intensive"
        },
        "provider_route": "openrouter",
        "provider_setting_label": "High",
        "reasoning_bracket": "intensive",
        "reasoning_bucket": "intensive",
        "reasoning_bucket_label": "High",
        "reasoning_catalog_sha256": "8cb3c2caa8990ee8d1189f73fa0e704a5d0ea7c014e5241f29fc7b3b2e1e3719",
        "reasoning_policy_version": "legacy_reasoning_845b695_to_kimi_k3_max_v1",
        "reasoning_request_mode": "effort",
        "requested_reasoning_effort": "high"
      },
      "reasoning_setting": "high",
      "repaired_admitted": null,
      "repaired_rate": null,
      "results_cut_id": "gb2-20260824-f35e2e58fce6",
      "row_kind": "game",
      "score": 24.174721344647317,
      "score_basis": "relative per-game score",
      "scoring_policy_version": "official_qualification_latest_effective_request_cohort_v14",
      "snapshot_id": "20260824_085407",
      "suite_line_id": "gamebench2",
      "suite_version": "2-known8-r3",
      "track_id": "full_freedom/intensive",
      "track_name": "Intensive filter",
      "uncertainty": 9.855626741889738,
      "unilateral_faults": 0,
      "wins": 0
    }
  ],
  "schema_version": 11,
  "snapshot_id": "20260824_085407",
  "suite_line_id": "gamebench2",
  "suite_version": "2-known8-r3"
}